Unsloth Releases Dynamic 2.0 GGUFs for Improved LLM Quantization
By
tosh
3mo ago· 5 min readenNews
97/100
Golden Brown
Bagelometer↗
A five-star bake. Worth schmearing, sharing, saving.
Score97TypenewsSentimentpositive
Summary
Unsloth has released Dynamic 2.0 GGUFs, a major upgrade to their quantization method for large language models. The new version outperforms leading quantization methods and sets new benchmarks for Aider Polglot, 5-shot MMLU, and KL Divergence. This allows users to run and fine-tune quantized LLMs while preserving maximum accuracy, with compatibility across most inference engines like llama.cpp and Unsloth Studio. The article announces the September 10, 2025 update with tougher benchmark results.
Key quotes
· 4 pulledWe're excited to introduce Unsloth Dynamic v2.0 quantization - a major upgrade to our previous quants.
This new method outperforms leading quantization methods and sets new benchmarks for Aider Polglot, 5-shot MMLU and KL Divergence.
This means you can now run + fine-tune quantized LLMs while preserving as much accuracy as possible!
You can run the 2.0 GGUFs on most inference engines like llama.cpp, Unsloth Studio etc.
A big new upgrade to our Dynamic Quants!
