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
- My AI/LLM predictions for the next 1, 3 and 6 years, for Oxide and Friends - 10th January 2025
- Weeknotes: Starting 2025 a little slow - 4th January 2025
- I still don't think companies serve you ads based on spying through your microphone - 2nd January 2025