qwen3.5-2b-MathVista : GGUF

• For text only LLMs: llama-cli -hf f416720001/qwen3.5-2b-MathVista --jinja
• For multimodal models: llama-mtmd-cli -hf f416720001/qwen3.5-2b-MathVista --jinja

Available Model files:

• Qwen3.5-2B.Q4_K_M.gguf
• Qwen3.5-2B.BF16-mmproj.gguf This was trained 2x faster with Unsloth