66 Downloads Updated 9 months ago
ollama run awaescher/qwen3-ud-q3:235b
ollama launch claude --model awaescher/qwen3-ud-q3:235b
ollama launch codex --model awaescher/qwen3-ud-q3:235b
ollama launch opencode --model awaescher/qwen3-ud-q3:235b
ollama launch openclaw --model awaescher/qwen3-ud-q3:235b
Merged gguf files from Unsloth’s Q3_K_XL from Qwen3:255b using the default modelfile with the recommended settings from Qwen.
This model will take about ~110GB VRAM with the default context window of 4096 tokens.