Qwen3-Coder 30B running locally in the @GitHub Copilot app (ollama) spitting ~85 tokens per second…
Burke Holland
Visit on X@burkeholland27K followers
24,262 views
Qwen3-Coder 30B running locally in the @GitHub Copilot app (ollama) spitting ~85 tokens per second on 96GB VRAM.
It's not Sol, but we're getting somewhere.
Comments
Comments from the original post on X (Twitter)
No comments yet
