Abliterated MiMo V2.6 Distill Qwen 9B GGUF MLX 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 GGUF MLX – a refusal‑ablated Qwen3.5 model
Abliterated MiMo V2.6 Distill Qwen 9B is a 9B agentic model derived from Xiaomi MiMo. It is quantized for local inference and focuses on text generation. The model is released under the MIT license.
Good at
- Text generation with reduced refusal
- Agentic tasks
- Coding and cybersecurity prompts
Limits
- No vision capability
- Safety evaluation incomplete
- Requires human oversight
Best for
- Research on refusal behavior
- Local inference experiments
- Controlled text generation
Who it’s for. Researchers and developers interested in local inference of a Qwen3.5 model with modified refusal behavior. The model is not suitable for safety‑critical or public deployment without controls.
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 (file size 5.63 GB, estimated memory 7.2 GB). If more memory is available, Q5_K_M (6.47 GB, 8 GB) or Q6_K (7.36 GB, 8.9 GB) provide higher quality. Q8_0 (9.53 GB, 11.1 GB) requires the most VRAM.
What GPU do you need for Abliterated MiMo V2.6 Distill Qwen 9B GGUF MLX?
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 GGUF MLX quant should you choose?
Q4_K_M is the usual starting point for Abliterated MiMo V2.6 Distill Qwen 9B GGUF MLX: 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 GGUF MLX
How much VRAM does Abliterated MiMo V2.6 Distill Qwen 9B GGUF MLX 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 GGUF MLX 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 MLX 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 GGUF MLX 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 MLX GGUF?
The files are on Hugging Face in the 0xSojalSec/Abliterated-MiMo-V2.6-Distill-Qwen-9B-GGUF-MLX 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 GGUF MLX 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, the Q4_K_M quant uses about 7.2 GB of VRAM at 8 k context, which fits within an 8 GB limit.
Does this model support vision?
No, the GGUF files are only evaluated for text generation.
Is the model safe for public deployment?
No, it requires human oversight and application controls due to incomplete safety evaluation.