megabytes/Home-Qwen3.5-0.8B-v0-GGUF

Home-Qwen3.5-0.8B-v0-GGUF

Home-Qwen3.5-0.8B-v0 is an experimental finetune for use in Home Assistant.

Why v0?

This is my first finetune ever, and frankly I would not be surprised if I broke something or did it wrong to begin with.

If It Just Works, Great :D! If you recognize an issue, please bring it to my attention.

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

• —For text only LLMs: llama-cli -hf megabytes/Home-Qwen3.5-0.8B-v0-GGUF --jinja
• —For multimodal models: llama-mtmd-cli -hf megabytes/Home-Qwen3.5-0.8B-v0-GGUF --jinja

Available Model files:

• —Qwen3.5-0.8B.Q8_0.gguf
• —Qwen3.5-0.8B.Q6_K.gguf
• —Qwen3.5-0.8B.Q4_K_M.gguf
• —Qwen3.5-0.8B.F16-mmproj.gguf This was trained 2x faster with Unsloth <img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>