MiMo V2.6 Distill Qwen 9B needs about 6.7 GB of memory at its main file (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.1 GB to 6.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
MiMo V2.6 Distill Qwen 9B – a 9B multimodal agentic model
MiMo V2.6 Distill Qwen 9B is a 9B agentic model built on Qwen3.5 architecture. It supports vision and general agent tasks such as coding, tool use, and cybersecurity. The model is released under the MIT license.
Good at
- Vision‑enabled agent tasks
- Coding and tool use
- General agentic reasoning
Limits
- No official MiMo release, community quantization only
- Large context requires 262144 tokens
- No explicit vision benchmark data
Best for
- Multimodal agent development
- Coding assistance with tool integration
- Research in agentic reinforcement learning
Who it’s for. Researchers and developers looking for a multimodal agentic model with a 9B parameter size. The model is suitable for experimentation in coding, tool use, and general agent tasks, and can be used with recent SGLang builds that support Qwen3.5.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 4.1 GB | 5.6 GB | Fits | Get file → | |
| — | 5.2 GB | 6.7 GB | Fits | Get file → | |
| — | 6.0 GB | 7.5 GB | Tight | Get file → |
For 8 GB VRAM, the 4.06 GiB file uses about 5.6 GiB of VRAM at 8 k context. The 5.17 GiB file uses about 6.7 GiB, and the 5.96 GiB file uses about 7.5 GiB. Choose the smallest file that fits your VRAM budget; the 4.06 GiB file is the most memory‑efficient option.
What GPU do you need for MiMo V2.6 Distill Qwen 9B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (4.1 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (6.0 GB file, about 7.5 GB in use).
Which MiMo V2.6 Distill Qwen 9B quant should you choose?
If memory is tight, the smallest file is the first one in the table at 4.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiMo V2.6 Distill Qwen 9B
How much VRAM does MiMo V2.6 Distill Qwen 9B need?
About 6.7 GB at its main file with an 8K context window. That is the 5.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run MiMo V2.6 Distill Qwen 9B on an 8 GB GPU?
Yes, with the smaller files: the 6.0 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiMo V2.6 Distill Qwen 9B GGUF?
It depends on the quant: file is 4.1 GB, file is 5.2 GB, file is 6.0 GB.
What context length does MiMo V2.6 Distill Qwen 9B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download MiMo V2.6 Distill Qwen 9B GGUF?
The files are on Hugging Face in the webmp3/Sakura-MiMo-V2.6-Distill-Qwen-9B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MiMo V2.6 Distill Qwen 9B use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run MiMo V2.6 Distill Qwen 9B on 8 GB VRAM?
Yes, the 4.06 GiB GGUF file uses approximately 5.6 GiB of VRAM at 8 k context, which fits within an 8 GB VRAM budget.
Does the model support vision tasks?
Yes, the model includes a vision projector and is detected to have vision capabilities.
What license applies to this model?
The model is released under the MIT license.