Qwen3.5-0.8B-1700-1704-mtp : GGUF

• For text only LLMs: llama-cli -hf l2repository/Qwen3.5-0.8B-1700-1704-mtp --jinja
• For multimodal models: llama-mtmd-cli -hf l2repository/Qwen3.5-0.8B-1700-1704-mtp --jinja

Available Model files:

• Qwen3.5-0.8B.F16.gguf
• Qwen3.5-0.8B.BF16-mmproj.gguf This was trained 2x faster with Unsloth