FastLLM support?
#17
by
lingyezhixing
- opened
It looks like the 80B/A13B is a great fit for fastllm inference on PCs with one or two GPUs, and it's much more appropriately sized than deepseek or Qwen3
It looks like the 80B/A13B is a great fit for fastllm inference on PCs with one or two GPUs, and it's much more appropriately sized than deepseek or Qwen3