Model Intelligence Sheet
ggml-org/MiMo-V2.6-Distill-Qwen-9B-GGUF overview
MiMo V2.6 Distill Qwen 9B Run with https://llama.app bash llama serve hf ggml org/MiMo V2.6 Distill Qwen 9B GGUF Source models https://huggingface.co/XiaomiMiM…
Runs locally from ~595.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | ggml-org/MiMo-V2.6-Distill-Qwen-9B-GGUF |
|---|---|
| Author | ggml-org |
| Pipeline | image-text-to-text |
| License | mit |
| Base model | XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B |
| Last modified | 2026-09-22T06:39:30.000Z |
Model README
---
license: mit
pipeline_tag: image-text-to-text
tags:
- gguf
- quantized
base_model:
- XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
---
MiMo-V2.6-Distill-Qwen-9B
Run with https://llama.app
llama serve -hf ggml-org/MiMo-V2.6-Distill-Qwen-9B-GGUFSource models
- https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Notes
- Includes a Q8_0 mmproj for the vision encoder.
- TODO: remove the chat template patch from convert.sh once the upstream template is fixed (interim fix: https://gist.github.com/coder543/d8f56cd6db67de4cafbb5bdb6c2dfb4d).
> [!IMPORTANT]
> This model is automatically converted using https://github.com/ggml-org/convert
Run ggml-org/MiMo-V2.6-Distill-Qwen-9B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models