Abliterated 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 4 quants, from 5.6 GB (Q4_K_M) to 9.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Abliterated MiMo V2.6 Distill Qwen 9B – a 9B agentic model with reduced refusal.
Abliterated MiMo V2.6 Distill Qwen 9B is a 9B parameter Qwen3.5‑based model fine‑tuned on MiMo data. It supports text generation only and includes a modified refusal mechanism. The model is released under the MIT license and is intended for research on local inference and refusal behavior.
Good at
- Text generation with agentic prompts
- Reduced refusal on harmful content
- Supports large context up to 262,144 tokens
Limits
- No vision capability
- Requires recent llama.cpp with Qwen3.5 support
- Safety evaluation incomplete – use with controls
Best for
- Research on refusal behavior
- Local inference with controlled outputs
- Testing large‑context text generation
Who it’s for. Researchers and developers who need a 9B Qwen model with a deliberately modified refusal mechanism for local inference. The model is suitable for experimentation but should not be used for safety‑critical or public deployments without human oversight.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| 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 → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K_M quant (5.63 GB file, ~7.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (6.47 GB, ~8 GB) or Q6_K (7.36 GB, ~8.9 GB) are suitable. The Q8_0 quant (9.53 GB, ~11.1 GB) requires more than 12 GB VRAM.
What GPU do you need for Abliterated 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: no quant fits at an 8K context.
- 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).
Which Abliterated MiMo V2.6 Distill Qwen 9B quant should you choose?
Q4_K_M is the usual starting point for Abliterated 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Abliterated MiMo V2.6 Distill Qwen 9B
How much VRAM does Abliterated 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 Abliterated 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 Abliterated MiMo V2.6 Distill Qwen 9B GGUF?
It depends on the quant: Q4_K_M is 5.6 GB, Q5_K_M is 6.5 GB, Q6_K is 7.4 GB, Q8_0 is 9.5 GB.
What context length does Abliterated 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 Abliterated MiMo V2.6 Distill Qwen 9B GGUF?
The files are on Hugging Face in the BoldingBuilds/Abliterated-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 Abliterated 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 this model on 8 GB VRAM?
Yes, using the Q4_K_M quant, which uses about 7.2 GB of VRAM at 8 k context.
Does this model support image input?
No, it is text‑only and does not have vision capability.
What license does it use?
The model is released under the MIT license.