Quantization matters (via) What impact does quantization have on the performance of an LLM? been wondering about this for quite a while, now here are numbers from Paul Gauthier.
He ran differently quantized versions of Qwen 2.5 32B Instruct through his Aider code editing benchmark and saw a range of scores.
The original released weights (BF16) scored highest at 71.4%, with Ollama's qwen2.5-coder:32b-instruct-fp16 (a 66GB download) achieving the same score.
The quantized Ollama qwen2.5-coder:32b-instruct-q4_K_M (a 20GB download) saw a massive drop in quality, scoring just 53.4% on the same benchmark.
Recent articles
- The Summer of Johann: prompt injections as far as the eye can see - 15th August 2025
- Open weight LLMs exhibit inconsistent performance across providers - 15th August 2025
- LLM 0.27, the annotated release notes: GPT-5 and improved tool calling - 11th August 2025