21:26
2026-08-17
forum.level1techs.com
large-language-models
Thoughts from existing B70 users?
Existing B70 users report that the best Intel LLM performance is achieved using a specific GitHub gist, with Qwen3.8-27B reaching 2313.29 tokens/s prefill and 30.76 tokens/s generation on a B70. One uā¦