Try poolside that came out yesterday https://news.ycombinator.com/item?id=49004937
or Qwen 3.5 122B A10B, both use more memory and still have experts sized for decent speed at the 395’s memory bandwidth at 4bit quantization
or Qwen 3.5 122B A10B, both use more memory and still have experts sized for decent speed at the 395’s memory bandwidth at 4bit quantization
No comments yet.