They host deepseek 4.1 flash and glm 5.3 you know. So mistral making LLM and hosting other LLM

Is tcq better than kvarn?

Llama.cpp themself is slow, lot of model lose their popularity.

What’s this 🤣 https://huggingface.co/richardyoung/Bev-9B-inverted

https://huggingface.co/collections/vllm-sr/decision-20

Ternary quant from prism-ml is not that good for complex task and long context. Probably fixable by using higher bit on certain tensor. As far I know for real world usage, at least non uniform 3 bit base is needed.