Simon Willison’s Weblog

llm-fragments-github 0.2. I upgraded my llm-fragments-github plugin to add a new fragment type called issue. It lets you pull the entire content of a GitHub issue thread into your prompt as a concatenated Markdown file.

(If you haven't seen fragments before I introduced them in Long context support in LLM 0.24 using fragments and template plugins.)

I used it just now to have Gemini 2.5 Pro provide feedback and attempt an implementation of a complex issue against my LLM project:

llm install llm-fragments-github
llm -f github:simonw/llm \
  -f issue:simonw/llm/938 \
  -m gemini-2.5-pro-exp-03-25 \
  --system 'muse on this issue, then propose a whole bunch of code to help implement it'

Here I'm loading the FULL content of the simonw/llm repo using that -f github:simonw/llm fragment (documented here), then loading all of the comments from issue 938 where I discuss quite a complex potential refactoring. I ask Gemini 2.5 Pro to "muse on this issue" and come up with some code.

This worked shockingly well. Here's the full response, which highlighted a few things I hadn't considered yet (such as the need to migrate old database records to the new tree hierarchy) and then spat out a whole bunch of code which looks like a solid start to the actual implementation work I need to do.

I ran this against Google's free Gemini 2.5 Preview, but if I'd used the paid model it would have cost me 202,680 input tokens and 10,460 output tokens for a total of 66.36 cents.

As a fun extra, the new issue: feature itself was written almost entirely by OpenAI o3, again using fragments. I ran this:

llm -m openai/o3 \
  -f https://raw.githubusercontent.com/simonw/llm-hacker-news/refs/heads/main/llm_hacker_news.py \
  -f https://raw.githubusercontent.com/simonw/tools/refs/heads/main/github-issue-to-markdown.html \
  -s 'Write a new fragments plugin in Python that registers issue:org/repo/123 which fetches that issue
      number from the specified github repo and uses the same markdown logic as the HTML page to turn that into a fragment'

Here I'm using the ability to pass a URL to -f and giving it the full source of my llm_hacker_news.py plugin (which shows how a fragment can load data from an API) plus the HTML source of my github-issue-to-markdown tool (which I wrote a few months ago with Claude). I effectively asked o3 to take that HTML/JavaScript tool and port it to Python to work with my fragments plugin mechanism.

o3 provided almost the exact implementation I needed, and even included support for a GITHUB_TOKEN environment variable without me thinking to ask for it. Total cost: 19.928 cents.

On a final note of curiosity I tried running this prompt against Gemma 3 27B QAT running on my Mac via MLX and llm-mlx:

llm install llm-mlx
llm mlx download-model mlx-community/gemma-3-27b-it-qat-4bit

llm -m mlx-community/gemma-3-27b-it-qat-4bit \
  -f https://raw.githubusercontent.com/simonw/llm-hacker-news/refs/heads/main/llm_hacker_news.py \
  -f https://raw.githubusercontent.com/simonw/tools/refs/heads/main/github-issue-to-markdown.html \
  -s 'Write a new fragments plugin in Python that registers issue:org/repo/123 which fetches that issue
      number from the specified github repo and uses the same markdown logic as the HTML page to turn that into a fragment'

That worked pretty well too. It turns out a 16GB local model file is powerful enough to write me an LLM plugin now!

# 20th April 2025, 2:01 pm / gemini, llm, ai-assisted-programming, generative-ai, o3, ai, llms, plugins, github, mlx, gemma, long-context, local-llms

Gemma 3 QAT Models. Interesting release from Google, as a follow-up to Gemma 3 from last month:

To make Gemma 3 even more accessible, we are announcing new versions optimized with Quantization-Aware Training (QAT) that dramatically reduces memory requirements while maintaining high quality. This enables you to run powerful models like Gemma 3 27B locally on consumer-grade GPUs like the NVIDIA RTX 3090.

I wasn't previously aware of Quantization-Aware Training but it turns out to be quite an established pattern now, supported in both Tensorflow and PyTorch.

Google report model size drops from BF16 to int4 for the following models:

• Gemma 3 27B: 54GB to 14.1GB
• Gemma 3 12B: 24GB to 6.6GB
• Gemma 3 4B: 8GB to 2.6GB
• Gemma 3 1B: 2GB to 0.5GB

They partnered with Ollama, LM Studio, MLX (here's their collection) and llama.cpp for this release - I'd love to see more AI labs following their example.

The Ollama model version picker currently hides them behind "View all" option, so here are the direct links:

• gemma3:1b-it-qat - 1GB
• gemma3:4b-it-qat - 4GB
• gemma3:12b-it-qat - 8.9GB
• gemma3:27b-it-qat - 18GB

I fetched that largest model with:

ollama pull gemma3:27b-it-qat

And now I'm trying it out with llm-ollama:

llm -m gemma3:27b-it-qat "impress me with some physics"

I got a pretty great response!

Update: Having spent a while putting it through its paces via Open WebUI and Tailscale to access my laptop from my phone I think this may be my new favorite general-purpose local model. Ollama appears to use 22GB of RAM while the model is running, which leaves plenty on my 64GB machine for other applications.

I've also tried it via llm-mlx like this (downloading 16GB):

llm install llm-mlx
llm mlx download-model mlx-community/gemma-3-27b-it-qat-4bit
llm chat -m mlx-community/gemma-3-27b-it-qat-4bit

It feels a little faster with MLX and uses 15GB of memory according to Activity Monitor.

# 19th April 2025, 5:20 pm / llm, ai, ollama, llms, gemma, llm-release, google, generative-ai, tailscale, mlx, local-llms

Qwen2.5-VL-32B: Smarter and Lighter. The second big open weight LLM release from China today - the first being DeepSeek v3-0324.

Qwen's previous vision model was Qwen2.5 VL, released in January in 3B, 7B and 72B sizes.

Today's Apache 2.0 licensed release is a 32B model, which is quickly becoming my personal favourite model size - large enough to have GPT-4-class capabilities, but small enough that on my 64GB Mac there's still enough RAM for me to run other memory-hungry applications like Firefox and VS Code.

Qwen claim that the new model (when compared to their previous 2.5 VL family) can "align more closely with human preferences", is better at "mathematical reasoning" and provides "enhanced accuracy and detailed analysis in tasks such as image parsing, content recognition, and visual logic deduction".

They also offer some presumably carefully selected benchmark results showing it out-performing Gemma 3-27B, Mistral Small 3.1 24B and GPT-4o-0513 (there have been two more recent GPT-4o releases since that one, 2024-08-16 and 2024-11-20).

As usual, Prince Canuma had MLX versions of the models live within hours of the release, in 4 bit, 6 bit, 8 bit, and bf16 variants.

I ran the 4bit version (a 18GB model download) using uv and Prince's mlx-vlm like this:

uv run --with 'numpy<2' --with mlx-vlm \
  python -m mlx_vlm.generate \
    --model mlx-community/Qwen2.5-VL-32B-Instruct-4bit \
    --max-tokens 1000 \
    --temperature 0.0 \
    --prompt "Describe this image." \
    --image Mpaboundrycdfw-1.png

Here's the image:

And here's the resulting description, which I found to be very impressive:

This image appears to be a map highlighting specific areas along the coastline, likely in California, based on the geographical features and place names. Here is a detailed description of the image:

1. Geographic Features:

   • The map shows a section of the coastline, with land on the right and the sea on the left.
   • The land area includes parts of SanMateo County, as noted in the top-right corner.
   • The coastline features several named locations, including:
     • Point Montara
     • Pillar Point
     • Kings Rock
     • VicenteCreek
     • DennistonCreek
     • State Beach

2. Highlighted Areas:

   • The map contains two distinct areas marked with different colors:
     • Red Area (Top Section)
       • Labeled as "MONTARA" and "MONTARA M R" (possibly referring to a "Marine Reserves" or similar protected area).
       • This area is marked with a dark red color and extends from the coastline inland.
     • Blue Area (Bottom Section)
       • Labeled as "PILLAR" and "PILLAR P O I N T" along with "SMCA" (Special Management Area).
       • This area is marked with a blue color and is located closer to the coastline, including the area around "Pillar Point."

3. Depth Contours:

   • The map includes depth markings in the sea, indicating the bathymetrical features:
     • 20 fathom (fm) line is marked in the upper-left part of the sea.
     • 10 fathom (fm) line is marked closer to the coastline.
     • 30 fathom (fm) line is marked further out to sea.

4. Other Features:

   • State Beach: Marked near the top-right, indicating a protected recreational area.
   • Kings Rock: A prominent feature near the coastline, likely a rocky outcropping.
   • Creeks: The map shows several creeks, including VicenteCreek and DennistonCreek, which flow into the sea.

5. Protected Areas:

   • The map highlights specific protected areas:
     • Marine Reserves:
       • "MONTARA M R" (Marine Reserves) in red.
     • Special Management Area (SMCA)
       • "PILLAR P O I N T" in blue, indicating a Special Management Area.

6. Grid and Coordinates:

   • The map includes a grid with latitude and longitude markings:
     • Latitude ranges from approximately 37°25'N to 37°35'N.
     • Longitude ranges from approximately 122°22.5'W to 122°35.5'W.

7. Topography:

   • The land area shows topographic features, including elevations and vegetation, with green areas indicating higher elevations or vegetated land.

8. Other Labels:

   • "SMR": Likely stands for "State Managed Reserves."
   • "SMCA": Likely stands for "Special Management Control Area."

In summary, this map highlights specific protected areas along the coastline, including a red "Marine Reserves" area and a blue "Special Management Area" near "Pillar Point." The map also includes depth markings, geographical features, and place names, providing a detailed view of the region's natural and protected areas.

It included the following runtime statistics:

Prompt: 1051 tokens, 111.985 tokens-per-sec
Generation: 760 tokens, 17.328 tokens-per-sec
Peak memory: 21.110 GB

# 24th March 2025, 10:43 pm / vision-llms, llm-release, generative-ai, ai, qwen, llms, uv, mlx, prince-canuma, local-llms

deepseek-ai/DeepSeek-V3-0324. Chinese AI lab DeepSeek just released the latest version of their enormous DeepSeek v3 model, baking the release date into the name DeepSeek-V3-0324.

The license is MIT (that's new - previous DeepSeek v3 had a custom license), the README is empty and the release adds up a to a total of 641 GB of files, mostly of the form model-00035-of-000163.safetensors.

The model only came out a few hours ago and MLX developer Awni Hannun already has it running at >20 tokens/second on a 512GB M3 Ultra Mac Studio ($9,499 of ostensibly consumer-grade hardware) via mlx-lm and this mlx-community/DeepSeek-V3-0324-4bit 4bit quantization, which reduces the on-disk size to 352 GB.

I think that means if you have that machine you can run it with my llm-mlx plugin like this, but I've not tried myself!

llm mlx download-model mlx-community/DeepSeek-V3-0324-4bit
llm chat -m mlx-community/DeepSeek-V3-0324-4bit

The new model is also listed on OpenRouter. You can try a chat at openrouter.ai/chat?models=deepseek/deepseek-chat-v3-0324:free.

Here's what the chat interface gave me for "Generate an SVG of a pelican riding a bicycle":

I have two API keys with OpenRouter - one of them worked with the model, the other gave me a No endpoints found matching your data policy error - I think because I had a setting on that key disallowing models from training on my activity. The key that worked was a free key with no attached billing credentials.

For my working API key the llm-openrouter plugin let me run a prompt like this:

llm install llm-openrouter
llm keys set openrouter
# Paste key here
llm -m openrouter/deepseek/deepseek-chat-v3-0324:free "best fact about a pelican"

Here's that "best fact" - the terminal output included Markdown and an emoji combo, here that's rendered.

One of the most fascinating facts about pelicans is their unique throat pouch, called a gular sac, which can hold up to 3 gallons (11 liters) of water—three times more than their stomach!

Here’s why it’s amazing:
- Fishing Tool: They use it like a net to scoop up fish, then drain the water before swallowing.
- Cooling Mechanism: On hot days, pelicans flutter the pouch to stay cool by evaporating water.
- Built-in "Shopping Cart": Some species even use it to carry food back to their chicks.

Bonus fact: Pelicans often fish cooperatively, herding fish into shallow water for an easy catch.

Would you like more cool pelican facts? 🐦🌊

In putting this post together I got Claude to build me this new tool for finding the total on-disk size of a Hugging Face repository, which is available in their API but not currently displayed on their website.

Update: Here's a notable independent benchmark from Paul Gauthier:

DeepSeek's new V3 scored 55% on aider's polyglot benchmark, significantly improving over the prior version. It's the #2 non-thinking/reasoning model, behind only Sonnet 3.7. V3 is competitive with thinking models like R1 & o3-mini.

# 24th March 2025, 3:04 pm / llm-release, hugging-face, generative-ai, deepseek, ai, llms, mlx, llm, ai-assisted-programming, tools, pelican-riding-a-bicycle, openrouter, local-llms

Mistral Small 3.1. Mistral Small 3 came out in January and was a notable, genuinely excellent local model that used an Apache 2.0 license.

Mistral Small 3.1 offers a significant improvement: it's multi-modal (images) and has an increased 128,000 token context length, while still "fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized" (according to their model card). Mistral's own benchmarks show it outperforming Gemma 3 and GPT-4o Mini, but I haven't seen confirmation from external benchmarks.

Despite their mention of a 32GB MacBook I haven't actually seen any quantized GGUF or MLX releases yet, which is a little surprising since they partnered with Ollama on launch day for their previous Mistral Small 3. I expect we'll see various quantized models released by the community shortly.

Update 20th March 2025: I've now run the text version on my laptop using mlx-community/Mistral-Small-3.1-Text-24B-Instruct-2503-8bit and llm-mlx:

llm mlx download-model mlx-community/Mistral-Small-3.1-Text-24B-Instruct-2503-8bit -a mistral-small-3.1
llm chat -m mistral-small-3.1

The model can be accessed via Mistral's La Plateforme API, which means you can use it via my llm-mistral plugin.

Here's the model describing my photo of two pelicans in flight:

llm install llm-mistral
# Run this if you have previously installed the plugin:
llm mistral refresh
llm -m mistral/mistral-small-2503 'describe' \
  -a https://static.simonwillison.net/static/2025/two-pelicans.jpg

The image depicts two brown pelicans in flight against a clear blue sky. Pelicans are large water birds known for their long bills and large throat pouches, which they use for catching fish. The birds in the image have long, pointed wings and are soaring gracefully. Their bodies are streamlined, and their heads and necks are elongated. The pelicans appear to be in mid-flight, possibly gliding or searching for food. The clear blue sky in the background provides a stark contrast, highlighting the birds' silhouettes and making them stand out prominently.

I added Mistral's API prices to my tools.simonwillison.net/llm-prices pricing calculator by pasting screenshots of Mistral's pricing tables into Claude.

# 17th March 2025, 6:45 pm / vision-llms, mistral, llm, generative-ai, ai, llms, ai-assisted-programming, llm-release, local-llms, mlx

mlx-community/OLMo-2-0325-32B-Instruct-4bit (via) OLMo 2 32B claims to be "the first fully-open model (all data, code, weights, and details are freely available) to outperform GPT3.5-Turbo and GPT-4o mini". Thanks to the MLX project here's a recipe that worked for me to run it on my Mac, via my llm-mlx plugin.

To install the model:

llm install llm-mlx
llm mlx download-model mlx-community/OLMo-2-0325-32B-Instruct-4bit

That downloads 17GB to ~/.cache/huggingface/hub/models--mlx-community--OLMo-2-0325-32B-Instruct-4bit.

To start an interactive chat with OLMo 2:

llm chat -m mlx-community/OLMo-2-0325-32B-Instruct-4bit

Or to run a prompt:

llm -m mlx-community/OLMo-2-0325-32B-Instruct-4bit 'Generate an SVG of a pelican riding a bicycle' -o unlimited 1

The -o unlimited 1 removes the cap on the number of output tokens - the default for llm-mlx is 1024 which isn't enough to attempt to draw a pelican.

The pelican it drew is refreshingly abstract:

# 16th March 2025, 3:30 am / llm, generative-ai, mlx, ai2, ai, llms, pelican-riding-a-bicycle, local-llms

QwQ-32B: Embracing the Power of Reinforcement Learning (via) New Apache 2 licensed reasoning model from Qwen:

We are excited to introduce QwQ-32B, a model with 32 billion parameters that achieves performance comparable to DeepSeek-R1, which boasts 671 billion parameters (with 37 billion activated). This remarkable outcome underscores the effectiveness of RL when applied to robust foundation models pretrained on extensive world knowledge.

I had a lot of fun trying out their previous QwQ reasoning model last November. I demonstrated this new QwQ in my talk at NICAR about recent LLM developments. Here's the example I ran.

LM Studio just released GGUFs ranging in size from 17.2 to 34.8 GB. MLX have compatible weights published in 3bit, 4bit, 6bit and 8bit. Ollama has the new qwq too - it looks like they've renamed the previous November release qwq:32b-preview.

# 5th March 2025, 9:10 pm / generative-ai, llm-reasoning, ai, qwen, llms, open-source, mlx, ollama, llm-release, local-llms

Qwen2.5 VL! Qwen2.5 VL! Qwen2.5 VL! Hot on the heels of yesterday's Qwen2.5-1M, here's Qwen2.5 VL (with an excitable announcement title) - the latest in Qwen's series of vision LLMs.

They're releasing multiple versions: base models and instruction tuned models at 3B, 7B and 72B. There's a lot of additional information in their README.

The 72B model can be selected on Qwen's Qwen Chat interface. I gave it this image of our dog Cleo joy rolling on the beach:

And prompted:

Describe this image in detail, be flowery

(Since the Qwen team tends to use flowery language in their announcements.)

Here's what I got back:

In this enchanting tableau, a canine companion finds solace in the embrace of nature's softest bed. The sandy expanse stretches out like an endless canvas, its surface etched with the delicate imprints of countless wanderers who have come and gone, leaving behind a tapestry of footprints that whisper tales of joyous romps and serene strolls.

The dog, a vision of contentment, lies sprawled upon the sand, its dark fur gleaming under the gentle caress of the sun. Its body is relaxed, limbs splayed in abandon, as if it has surrendered to the soothing rhythm of the beach. A vibrant red collar adorns its neck, a splash of color against the muted tones of the surroundings, hinting at the care and love bestowed upon this cherished pet.

The sand itself is a work of art, its grains shimmering with a silvery sheen that catches the light. Here and there, small tufts of seaweed peek through, remnants of the ocean's bounty, adding a touch of wild beauty to the scene. The shadows cast by unseen objects dance across the sand, creating a play of light and dark that lends an air of mystery to the tranquil setting.

This moment, frozen in time, speaks of peace and harmony, where man's best friend finds respite in the simple pleasures of life. It is a scene that invites one to pause, breathe deeply, and revel in the serenity of nature's embrace.

I'm looking forward to trying out their smaller models - the 3B model in particular should be small enough to run comfortably even on an iPhone, so hopefully someone will wire up an example of that soon (maybe using MLX).

VB points out that the vision benchmarks for Qwen 2.5 VL 7B show it out-performing GPT-4o mini!

Qwen2.5 VL cookbooks

Qwen also just published a set of cookbook recipes:

• universal_recognition.ipynb demonstrates basic visual Q&A, including prompts like Who are these in this picture? Please give their names in Chinese and English against photos of celebrities, an ability other models have deliberately suppressed.
• spatial_understanding.ipynb demonstrates bounding box support, with prompts like Locate the top right brown cake, output its bbox coordinates using JSON format.
• video_understanding.ipynb breaks a video into individual frames and asks questions like Could you go into detail about the content of this long video?
• ocr.ipynb shows Qwen2.5-VL-7B-Instruct performing OCR in multiple different languages.
• document_parsing.ipynb uses Qwen to convert images of documents to HTML and other formats, and notes that "we introduce a unique Qwenvl HTML format that includes positional information for each component, enabling precise document reconstruction and manipulation."
• mobile_agent.ipynb runs Qwen with tool use against tools for controlling a mobile phone, similar to ChatGPT Operator or Claude Computer Use.
• computer_use.ipynb showcases "GUI grounding" - feeding in screenshots of a user's desktop and running tools for things like left clicking on a specific coordinate.

Running it with mlx-vlm

Update 30th January 2025: I got it working on my Mac using uv and mlx-vlm, with some hints from this issue. Here's the recipe that worked (downloading a 9GB model from mlx-community/Qwen2.5-VL-7B-Instruct-8bit):

uv run --with 'numpy<2' --with 'git+https://github.com/huggingface/transformers' \
  --with mlx-vlm \
  python -m mlx_vlm.generate \
    --model mlx-community/Qwen2.5-VL-7B-Instruct-8bit \
    --max-tokens 100 \
    --temp 0.0 \
    --prompt "Describe this image." \
    --image path-to-image.png

I ran that against this image:

And got back this result:

The image appears to illustrate a flowchart or diagram related to a cybersecurity scenario. Here's a breakdown of the elements:

1. User: Represented by a simple icon of a person.
2. AI Agent: Represented by a blue diamond shape.
3. Attacker: Represented by a red icon of a person.
4. Cloud and Email Icons: Represented by a cloud and an envelope, indicating data or information being transferred.
5. Text: The text

# 27th January 2025, 8:05 pm / vision-llms, generative-ai, ai, qwen, llms, prompt-engineering, ocr, uv, mlx, local-llms

The impact of competition and DeepSeek on Nvidia (via) Long, excellent piece by Jeffrey Emanuel capturing the current state of the AI/LLM industry. The original title is "The Short Case for Nvidia Stock" - I'm using the Hacker News alternative title here, but even that I feel under-sells this essay.

Jeffrey has a rare combination of experience in both computer science and investment analysis. He combines both worlds here, evaluating NVIDIA's challenges by providing deep insight into a whole host of relevant and interesting topics.

As Jeffrey describes it, NVIDA's moat has four components: high-quality Linux drivers, CUDA as an industry standard, the fast GPU interconnect technology they acquired from Mellanox in 2019 and the flywheel effect where they can invest their enormous profits (75-90% margin in some cases!) into more R&D.

Each of these is under threat.

Technologies like MLX, Triton and JAX are undermining the CUDA advantage by making it easier for ML developers to target multiple backends - plus LLMs themselves are getting capable enough to help port things to alternative architectures.

GPU interconnect helps multiple GPUs work together on tasks like model training. Companies like Cerebras are developing enormous chips that can get way more done on a single chip.

Those 75-90% margins provide a huge incentive for other companies to catch up - including the customers who spend the most on NVIDIA at the moment - Microsoft, Amazon, Meta, Google, Apple - all of whom have their own internal silicon projects:

Now, it's no secret that there is a strong power law distribution of Nvidia's hyper-scaler customer base, with the top handful of customers representing the lion's share of high-margin revenue. How should one think about the future of this business when literally every single one of these VIP customers is building their own custom chips specifically for AI training and inference?

The real joy of this article is the way it describes technical details of modern LLMs in a relatively accessible manner. I love this description of the inference-scaling tricks used by O1 and R1, compared to traditional transformers:

Basically, the way Transformers work in terms of predicting the next token at each step is that, if they start out on a bad "path" in their initial response, they become almost like a prevaricating child who tries to spin a yarn about why they are actually correct, even if they should have realized mid-stream using common sense that what they are saying couldn't possibly be correct.

Because the models are always seeking to be internally consistent and to have each successive generated token flow naturally from the preceding tokens and context, it's very hard for them to course-correct and backtrack. By breaking the inference process into what is effectively many intermediate stages, they can try lots of different things and see what's working and keep trying to course-correct and try other approaches until they can reach a fairly high threshold of confidence that they aren't talking nonsense.

The last quarter of the article talks about the seismic waves rocking the industry right now caused by DeepSeek v3 and R1. v3 remains the top-ranked open weights model, despite being around 45x more efficient in training than its competition: bad news if you are selling GPUs! R1 represents another huge breakthrough in efficiency both for training and for inference - the DeepSeek R1 API is currently 27x cheaper than OpenAI's o1, for a similar level of quality.

Jeffrey summarized some of the key ideas from the v3 paper like this:

A major innovation is their sophisticated mixed-precision training framework that lets them use 8-bit floating point numbers (FP8) throughout the entire training process. [...]

DeepSeek cracked this problem by developing a clever system that breaks numbers into small tiles for activations and blocks for weights, and strategically uses high-precision calculations at key points in the network. Unlike other labs that train in high precision and then compress later (losing some quality in the process), DeepSeek's native FP8 approach means they get the massive memory savings without compromising performance. When you're training across thousands of GPUs, this dramatic reduction in memory requirements per GPU translates into needing far fewer GPUs overall.

Then for R1:

With R1, DeepSeek essentially cracked one of the holy grails of AI: getting models to reason step-by-step without relying on massive supervised datasets. Their DeepSeek-R1-Zero experiment showed something remarkable: using pure reinforcement learning with carefully crafted reward functions, they managed to get models to develop sophisticated reasoning capabilities completely autonomously. This wasn't just about solving problems— the model organically learned to generate long chains of thought, self-verify its work, and allocate more computation time to harder problems.

The technical breakthrough here was their novel approach to reward modeling. Rather than using complex neural reward models that can lead to "reward hacking" (where the model finds bogus ways to boost their rewards that don't actually lead to better real-world model performance), they developed a clever rule-based system that combines accuracy rewards (verifying final answers) with format rewards (encouraging structured thinking). This simpler approach turned out to be more robust and scalable than the process-based reward models that others have tried.

This article is packed with insights like that - it's worth spending the time absorbing the whole thing.

# 27th January 2025, 1:55 am / cerebras, nvidia, generative-ai, deepseek, ai, llms, mlx, llm-reasoning

Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens (via) Very significant new release from Alibaba's Qwen team. Their openly licensed (sometimes Apache 2, sometimes Qwen license, I've had trouble keeping up) Qwen 2.5 LLM previously had an input token limit of 128,000 tokens. This new model increases that to 1 million, using a new technique called Dual Chunk Attention, first described in this paper from February 2024.

They've released two models on Hugging Face: Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, both requiring CUDA and both under an Apache 2.0 license.

You'll need a lot of VRAM to run them at their full capacity:

VRAM Requirement for processing 1 million-token sequences:

• Qwen2.5-7B-Instruct-1M: At least 120GB VRAM (total across GPUs).
• Qwen2.5-14B-Instruct-1M: At least 320GB VRAM (total across GPUs).

If your GPUs do not have sufficient VRAM, you can still use Qwen2.5-1M models for shorter tasks.

Qwen recommend using their custom fork of vLLM to serve the models:

You can also use the previous framework that supports Qwen2.5 for inference, but accuracy degradation may occur for sequences exceeding 262,144 tokens.

GGUF quantized versions of the models are already starting to show up. LM Studio's "official model curator" Bartowski published lmstudio-community/Qwen2.5-7B-Instruct-1M-GGUF and lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF - sizes range from 4.09GB to 8.1GB for the 7B model and 7.92GB to 15.7GB for the 14B.

These might not work well yet with the full context lengths as the underlying llama.cpp library may need some changes.

I tried running the 8.1GB 7B model using Ollama on my Mac like this:

ollama run hf.co/lmstudio-community/Qwen2.5-7B-Instruct-1M-GGUF:Q8_0

Then with LLM:

llm install llm-ollama
llm models -q qwen # To search for the model ID
# I set a shorter q1m alias:
llm aliases set q1m hf.co/lmstudio-community/Qwen2.5-7B-Instruct-1M-GGUF:Q8_0

I tried piping a large prompt in using files-to-prompt like this:

files-to-prompt ~/Dropbox/Development/llm -e py -c | llm -m q1m 'describe this codebase in detail'

That should give me every Python file in my llm project. Piping that through ttok first told me this was 63,014 OpenAI tokens, I expect that count is similar for Qwen.

The result was disappointing: it appeared to describe just the last Python file that stream. Then I noticed the token usage report:

2,048 input, 999 output

This suggests to me that something's not working right here - maybe the Ollama hosting framework is truncating the input, or maybe there's a problem with the GGUF I'm using?

I'll update this post when I figure out how to run longer prompts through the new Qwen model using GGUF weights on a Mac.

Update: It turns out Ollama has a num_ctx option which defaults to 2048, affecting the input context length. I tried this:

files-to-prompt \
  ~/Dropbox/Development/llm \
  -e py -c | \
llm -m q1m 'describe this codebase in detail' \
 -o num_ctx 80000

But I quickly ran out of RAM (I have 64GB but a lot of that was in use already) and hit Ctrl+C to avoid crashing my computer. I need to experiment a bit to figure out how much RAM is used for what context size.

Awni Hannun shared tips for running mlx-community/Qwen2.5-7B-Instruct-1M-4bit using MLX, which should work for up to 250,000 tokens. They ran 120,000 tokens and reported:

• Peak RAM for prompt filling was 22GB
• Peak RAM for generation 12GB
• Prompt filling took 350 seconds on an M2 Ultra
• Generation ran at 31 tokens-per-second on M2 Ultra

# 26th January 2025, 6:54 pm / llms, ai, qwen, generative-ai, llm, ollama, long-context, llama-cpp, llm-release, files-to-prompt, local-llms, mlx

Run DeepSeek R1 or V3 with MLX Distributed (via) Handy detailed instructions from Awni Hannun on running the enormous DeepSeek R1 or v3 models on a cluster of Macs using the distributed communication feature of Apple's MLX library.

DeepSeek R1 quantized to 4-bit requires 450GB in aggregate RAM, which can be achieved by a cluster of three 192 GB M2 Ultras ($16,797 will buy you three 192GB Apple M2 Ultra Mac Studios at $5,599 each).

# 22nd January 2025, 4:15 am / apple, generative-ai, mlx, deepseek, ai, llms, local-llms

microsoft/phi-4. Here's the official release of Microsoft's Phi-4 LLM, now officially under an MIT license.

A few weeks ago I covered the earlier unofficial versions, where I talked about how the model used synthetic training data in some really interesting ways.

It benchmarks favorably compared to GPT-4o, suggesting this is yet another example of a GPT-4 class model that can run on a good laptop.

The model already has several available community quantizations. I ran the mlx-community/phi-4-4bit one (a 7.7GB download) using mlx-llm like this:

uv run --with 'numpy<2' --with mlx-lm python -c '
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/phi-4-4bit")

prompt = "Generate an SVG of a pelican riding a bicycle"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True, max_tokens=2048)
print(response)'

Here's what I got back.

Update: The model is now available via Ollama, so you can fetch a 9.1GB model file using ollama run phi4, after which it becomes available via the llm-ollama plugin.

# 8th January 2025, 5:57 pm / phi, generative-ai, ai, microsoft, llms, uv, pelican-riding-a-bicycle, llm, ollama, llm-release, local-llms, mlx

Meta AI release Llama 3.3. This new Llama-3.3-70B-Instruct model from Meta AI makes some bold claims:

This model delivers similar performance to Llama 3.1 405B with cost effective inference that’s feasible to run locally on common developer workstations.

I have 64GB of RAM in my M2 MacBook Pro, so I'm looking forward to trying a slightly quantized GGUF of this model to see if I can run it while still leaving some memory free for other applications.

Update: Ollama have a 43GB GGUF available now. And here's an MLX 8bit version and other MLX quantizations.

Llama 3.3 has 70B parameters, a 128,000 token context length and was trained to support English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

The model card says that the training data was "A new mix of publicly available online data" - 15 trillion tokens with a December 2023 cut-off.

They used "39.3M GPU hours of computation on H100-80GB (TDP of 700W) type hardware" which they calculate as 11,390 tons CO2eq. I believe that's equivalent to around 20 fully loaded passenger flights from New York to London (at ~550 tons per flight).

Update 19th January 2025: On further consideration I no longer trust my estimate here: it's surprisingly hard to track down reliable numbers but I think the total CO2 used by those flights may be more in the order of 200-400 tons, so my estimate for Llama 3.3 70B should have been more in the order of between 28 and 56 flights. Don't trust those numbers either though!

# 6th December 2024, 6:30 pm / meta, generative-ai, llama, training-data, ai, local-llms, llms, ollama, llm-release, mlx

SmolVLM—small yet mighty Vision Language Model. I've been having fun playing with this new vision model from the Hugging Face team behind SmolLM. They describe it as:

[...] a 2B VLM, SOTA for its memory footprint. SmolVLM is small, fast, memory-efficient, and fully open-source. All model checkpoints, VLM datasets, training recipes and tools are released under the Apache 2.0 license.

I've tried it in a few flavours but my favourite so far is the mlx-vlm approach, via mlx-vlm author Prince Canuma. Here's the uv recipe I'm using to run it:

uv run \
  --with mlx-vlm \
  --with torch \
  python -m mlx_vlm.generate \
    --model mlx-community/SmolVLM-Instruct-bf16 \
    --max-tokens 500 \
    --temp 0.5 \
    --prompt "Describe this image in detail" \
    --image IMG_4414.JPG

If you run into an error using Python 3.13 (torch compatibility) try uv run --python 3.11 instead.

This one-liner installs the necessary dependencies, downloads the model (about 4.2GB, saved to ~/.cache/huggingface/hub/models--mlx-community--SmolVLM-Instruct-bf16) and executes the prompt and displays the result.

I ran that against this Pelican photo:

The model replied:

In the foreground of this photograph, a pelican is perched on a pile of rocks. The pelican’s wings are spread out, and its beak is open. There is a small bird standing on the rocks in front of the pelican. The bird has its head cocked to one side, and it seems to be looking at the pelican. To the left of the pelican is another bird, and behind the pelican are some other birds. The rocks in the background of the image are gray, and they are covered with a variety of textures. The rocks in the background appear to be wet from either rain or sea spray.

There are a few spatial mistakes in that description but the vibes are generally in the right direction.

On my 64GB M2 MacBook pro it read the prompt at 7.831 tokens/second and generated that response at an impressive 74.765 tokens/second.

# 28th November 2024, 8:29 pm / vision-llms, uv, mlx, ai, local-llms, llms, python, generative-ai, smollm, llm-release, prince-canuma

Whisper large-v3-turbo model. It’s OpenAI DevDay today. Last year they released a whole stack of new features, including GPT-4 vision and GPTs and their text-to-speech API, so I’m intrigued to see what they release today (I’ll be at the San Francisco event).

Looks like they got an early start on the releases, with the first new Whisper model since November 2023.

Whisper Turbo is a new speech-to-text model that fits the continued trend of distilled models getting smaller and faster while maintaining the same quality as larger models.

large-v3-turbo is 809M parameters - slightly larger than the 769M medium but significantly smaller than the 1550M large. OpenAI claim its 8x faster than large and requires 6GB of VRAM compared to 10GB for the larger model.

The model file is a 1.6GB download. OpenAI continue to make Whisper (both code and model weights) available under the MIT license.

It’s already supported in both Hugging Face transformers - live demo here - and in mlx-whisper on Apple Silicon, via Awni Hannun:

import mlx_whisper
print(mlx_whisper.transcribe(
  "path/to/audio",
  path_or_hf_repo="mlx-community/whisper-turbo"
)["text"])

Awni reports:

Transcribes 12 minutes in 14 seconds on an M2 Ultra (~50X faster than real time).

# 1st October 2024, 3:13 pm / openai, whisper, ai, mlx

mlx-vlm (via) The MLX ecosystem of libraries for running machine learning models on Apple Silicon continues to expand. Prince Canuma is actively developing this library for running vision models such as Qwen-2 VL and Pixtral and LLaVA using Python running on a Mac.

I used uv to run it against this image with this shell one-liner:

uv run --with mlx-vlm \
  python -m mlx_vlm.generate \
  --model Qwen/Qwen2-VL-2B-Instruct \
  --max-tokens 1000 \
  --temp 0.0 \
  --image https://static.simonwillison.net/static/2024/django-roadmap.png \
  --prompt "Describe image in detail, include all text"

The --image option works equally well with a URL or a path to a local file on disk.

This first downloaded 4.1GB to my ~/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct folder and then output this result, which starts:

The image is a horizontal timeline chart that represents the release dates of various software versions. The timeline is divided into years from 2023 to 2029, with each year represented by a vertical line. The chart includes a legend at the bottom, which distinguishes between different types of software versions.

Legend

Mainstream Support:

• 4.2 (2023)
• 5.0 (2024)
• 5.1 (2025)
• 5.2 (2026)
• 6.0 (2027) [...]

# 29th September 2024, 9:38 pm / vision-llms, apple, python, generative-ai, uv, ai, llms, mlx, qwen, prince-canuma, local-llms

Moshi (via) Moshi is "a speech-text foundation model and full-duplex spoken dialogue framework". It's effectively a text-to-text model - like an LLM but you input audio directly to it and it replies with its own audio.

It's fun to play around with, but it's not particularly useful in comparison to other pure text models: I tried to talk to it about California Brown Pelicans and it gave me some very basic hallucinated thoughts about California Condors instead.

It's very easy to run locally, at least on a Mac (and likely on other systems too). I used uv and got the 8 bit quantized version running as a local web server using this one-liner:

uv run --with moshi_mlx python -m moshi_mlx.local_web -q 8

That downloads ~8.17G of model to a folder in ~/.cache/huggingface/hub/ - or you can use -q 4 and get a 4.81G version instead (albeit even lower quality).

# 19th September 2024, 6:20 pm / generative-ai, uv, text-to-speech, ai, llms, mlx

mlx-whisper (via) Apple's MLX framework for running GPU-accelerated machine learning models on Apple Silicon keeps growing new examples. mlx-whisper is a Python package for running OpenAI's Whisper speech-to-text model. It's really easy to use:

pip install mlx-whisper

Then in a Python console:

>>> import mlx_whisper
>>> result = mlx_whisper.transcribe(
...    "/tmp/recording.mp3",
...     path_or_hf_repo="mlx-community/distil-whisper-large-v3")
.gitattributes: 100%|███████████| 1.52k/1.52k [00:00<00:00, 4.46MB/s]
config.json: 100%|██████████████| 268/268 [00:00<00:00, 843kB/s]
README.md: 100%|████████████████| 332/332 [00:00<00:00, 1.95MB/s]
Fetching 4 files:  50%|████▌    | 2/4 [00:01<00:01,  1.26it/s]
weights.npz:  63%|██████████  ▎ | 944M/1.51G [02:41<02:15, 4.17MB/s]
>>> result.keys()
dict_keys(['text', 'segments', 'language'])
>>> result['language']
'en'
>>> len(result['text'])
100105
>>> print(result['text'][:3000])
 This is so exciting. I have to tell you, first of all ...

Here's Activity Monitor confirming that the Python process is using the GPU for the transcription:

This example downloaded a 1.5GB model from Hugging Face and stashed it in my ~/.cache/huggingface/hub/models--mlx-community--distil-whisper-large-v3 folder.

Calling .transcribe(filepath) without the path_or_hf_repo argument uses the much smaller (74.4 MB) whisper-tiny-mlx model.

A few people asked how this compares to whisper.cpp. Bill Mill compared the two and found mlx-whisper to be about 3x faster on an M1 Max.

Update: this note from Josh Marshall:

That '3x' comparison isn't fair; completely different models. I ran a test (14" M1 Pro) with the full (non-distilled) large-v2 model quantised to 8 bit (which is my pick), and whisper.cpp was 1m vs 1m36 for mlx-whisper.

Then later:

I've now done a better test, using the MLK audio, multiple runs and 2 models (distil-large-v3, large-v2-8bit)... and mlx-whisper is indeed 30-40% faster

# 13th August 2024, 4:15 pm / apple, python, openai, whisper, ai, mlx