Re:Kimi Linear: An Expressive, Efficient Attention Architecture
by embedding-shape on Friday October 31, 2025 @09:54AM
(#45772009)
How many tok/s are you getting (with any runtime) with either the Kimi-Linear-Instruct or Kimi-Linear-Base on your RTX 3070?
[ Parent
| on HN ]
Re:Kimi Linear: An Expressive, Efficient Attention Architecture
by samus on Friday October 31, 2025 @04:09PM
(#45776165)
With a Qwen3-32B-A3B (Q8) I'm getting 10-20 t/sec on KoboldAI, e.g., llama cpp. Faster than I can read, so good enough for hobby use. I expect this model to be significantly faster, but llama.cpp-based software probably doesn't support it yet.