alt Hacker NewsNice! Does anyone know how this compares to the Unsloth quantizations of this model? https://unsloth.ai/docs/models/qwen3.8#run-qwen3.8-guide
Replies
0xbadcafebee • yesterday at 11:57 PM
Came to ask the same. From my really rough understanding, it seems like Unsloth's method allows a slightly higher precision at a higher file size, while PrismML's uses a different approach to achieve a smaller size (and presumably less precision).
There's a table on the HF page that compares it against Unsloth's UD-Q4_K_XL and IQ2_XXS: https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf#fu...