Qwen3.5-2b-code : GGUF

• For text only LLMs: llama-cli -hf Pranjalps1/Qwen3.5-2b-code --jinja
• For multimodal models: llama-mtmd-cli -hf Pranjalps1/Qwen3.5-2b-code --jinja

Available Model files:

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