466 Downloads Updated 1 year ago
ollama run sammcj/qwen2.5-coder-32b-128k:q6_k
ollama launch claude --model sammcj/qwen2.5-coder-32b-128k:q6_k
ollama launch codex --model sammcj/qwen2.5-coder-32b-128k:q6_k
ollama launch opencode --model sammcj/qwen2.5-coder-32b-128k:q6_k
ollama launch openclaw --model sammcj/qwen2.5-coder-32b-128k:q6_k
This uses Unsloth’s GGUF which fixes the context length (the official Ollama model is wrong).