Benjamin Marie(@bnjmn_marie):Coming later today: statistically lossless quantization for Qwen3.8 27B, GGUF versions! > Better than the GPTQ versions published last week https://t.co/UYBd96XK7h > Made from Unsloth's best UD GGUFs btw, when running this process, I found that Unsloth's UD Q8 K XL matches the original BF16 next-token full vocab probability distribution at 99.5%. That's insanely high and significantly better than the official FP8. Unbeatable.

Benjamin Marie

@bnjmn_marie

Independent AI researcher (AI, LLM). Support my work:

Joined June 2019

227 Following 7.7K Followers

Benjamin Marie@bnjmn_marie

2026.10.26 17:19

Coming later today: statistically lossless quantization for Qwen3.8 27B, GGUF versions! > Better than the GPTQ versions published last week > Made from Unsloth's best UD GGUFs btw, when running this process, I found that Unsloth's UD Q8 K XL matches the original BF16 next-token full vocab probability distribution at 99.5%. That's insanely high and significantly better than the official FP8. Unbeatable.