MiMo V2.6 Distill Qwen 9B needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 18 quants, from 3.6 GB (IQ2_M) to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
MiMo V2.6 Distill Qwen 9B – 9B agentic model with vision and tool use
MiMo V2.6 Distill Qwen 9B is a 9B agentic model based on Qwen3.5-9B. It supports text, vision, and tool usage. The model was fine‑tuned on 77.4B tokens of MiMo data.
Good at
- Vision‑enabled agent tasks
- Tool‑aware code generation
- Japanese instruction following
Limits
- Large context of 262144 tokens increases VRAM usage
- Requires a separate mmproj file for vision
- MIT license limits commercial use without attribution
Best for
- Developing agentic applications
- Generating code with tool calls
- Processing images with text prompts
Who it’s for. The model is suited for researchers and developers building agentic systems that need vision and tool integration. It is ideal for open‑source projects that can handle the MIT license and the requirement of a separate vision projector.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q2_K | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q2_K | 3.8 GB | 5.4 GB | Fits | Get file → | |
| IQ3_M | 4.4 GB | 6.0 GB | Fits | Get file → | |
| IQ3_M | 4.4 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| BF16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, IQ2_M (file size 3.61 GB, memory 5.2 GB at 8 k context) is recommended. If more VRAM is available, Q4_K_M (5.63 GB, 7.2 GB) or Q5_K_M (6.47 GB, 8 GB) provide higher quality. BF16 (17.92 GB, 19.5 GB) offers the best precision but needs large memory.
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 IQ3_M (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).
Which MiMo V2.6 Distill Qwen 9B quant should you choose?
Q4_K_M is the usual starting point for MiMo V2.6 Distill Qwen 9B: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ2_M at 3.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Q5_K_M: the 6.5 GB file needs about 8.0 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: IQ2_M is 3.6 GB, Q2_K is 3.8 GB, Q2_K is 3.8 GB, IQ3_M is 4.4 GB, IQ3_M is 4.4 GB, Q3_K_M is 4.6 GB and 12 more.
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 Quantelium/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 IQ2_M on 8 GB VRAM?
Yes, IQ2_M requires about 5.2 GB at 8 k context, which fits within 8 GB VRAM.
Do I need a separate mmproj file for vision?
Yes, the vision projector is a separate file and can be combined with any GGUF quantization.
Is the model licensed for commercial use?
The model is MIT licensed; commercial use is allowed with attribution.