MiMo V2.6 Distill Qwen 9B Ablit 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 12 quants, from 3.8 GB (Q2_K) to 17.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
MiMo V2.6 Distill Qwen 9B Ablit – a 9B Qwen model with baked refusal ablation
MiMo V2.6 Distill Qwen 9B Ablit is a 8.95B parameter Qwen‑35 model. It contains a baked refusal‑ablation that removes refusal phrasing while preserving deflection behavior. The model supports tools and vision, and is released under the MIT license.
Good at
- Tools and vision support
- Baked refusal ablation
- Large context of 262144 tokens
Limits
- No runtime hooks or LoRA
- No quantized derivatives released yet
- No image input measured
Best for
- Developers needing refusal‑ablation in a Qwen model
- Applications requiring tool calls
- Projects needing a 262144‑token context
Who it’s for. Engineers and researchers building applications that need a Qwen model with built‑in refusal ablation. The model is suitable for developers who prefer a plain BF16 checkpoint and plan to quantize themselves.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_S | 5.4 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_S | 6.3 GB | 7.9 GB | Tight | 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 → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| F16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.63 GB, estimated memory 7.2 GB). For 12 GB VRAM, Q5_K_M (6.47 GB, 8 GB) or Q6_K (7.36 GB, 8.9 GB) are suitable. For 16 GB VRAM, Q8_0 (9.53 GB, 11.1 GB) or F16 (17.92 GB, 19.5 GB) provide higher quality.
What GPU do you need for MiMo V2.6 Distill Qwen 9B Ablit?
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 Q3_K_S (4.3 GB file, about 5.8 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 F16 (17.9 GB file, about 19.5 GB in use).
Which MiMo V2.6 Distill Qwen 9B Ablit quant should you choose?
Q4_K_M is the usual starting point for MiMo V2.6 Distill Qwen 9B Ablit: 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 Q2_K at 3.8 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
Frequently asked questions about MiMo V2.6 Distill Qwen 9B Ablit
How much VRAM does MiMo V2.6 Distill Qwen 9B Ablit 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 Ablit 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 Ablit GGUF?
It depends on the quant: Q2_K is 3.8 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.6 GB, Q3_K_L is 4.9 GB, IQ4_XS is 5.2 GB, Q4_K_S is 5.4 GB and 6 more.
What context length does MiMo V2.6 Distill Qwen 9B Ablit 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 Ablit GGUF?
The files are on Hugging Face in the mradermacher/MiMo-V2.6-Distill-Qwen-9B-ablit-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 Ablit 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 Ablit on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 7.2 GB of VRAM at 8 k context.
Does the model support vision?
Yes, the model has detected vision ability, but image input has not been measured.
Is there a quantized version available?
Only the BF16 checkpoint is released; quantized derivatives are planned but not yet available.