QW

MiMo V2.6 Distill Qwen 9B Abliterated

QwenGGUF by geantendormiUpdated 2026-09-22
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant4.4 GB
Quick answer

MiMo V2.6 Distill Qwen 9B Abliterated needs about 6.0 GB of memory at IQ3_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.4 GB (IQ3_M) 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 Abliterated – 8.95B parameter Qwen3.5 model

MiMo V2.6 Distill Qwen 9B Abliterated is a 8.95B parameter Qwen3.5 architecture model distilled from Xiaomi MiMo. It supports 262144 context tokens and is available in GGUF format with two quantizations: IQ3_M and F16.

Good at

  • Large context handling
  • High safety rejection
  • Strong math reasoning

Limits

  • No vision support
  • License not specified
  • No mixture of experts

Best for

  • Long‑form text generation
  • Safety‑critical dialogue
  • Academic math problem solving

Who it’s for. Developers building applications that require long context and high safety. Researchers needing a Qwen3.5 model with extensive context tokens and robust safety features.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M4.4 GB 6.0 GB
Fits Get file →
F1617.9 GB 19.5 GB
Too big Get file →

For 8‑12 GB VRAM use the IQ3_M quant (4.42 GB file, ~6 GB VRAM at 8 k context). For 16 GB VRAM or higher use the F16 quant (17.92 GB file, ~19.5 GB VRAM at 8 k context). Memory estimates are approximate.

What GPU do you need for MiMo V2.6 Distill Qwen 9B Abliterated?

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 IQ3_M (4.4 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_M (4.4 GB file, about 6.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (4.4 GB file, about 6.0 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 Abliterated quant should you choose?

IQ3_M (4.4 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bygeantendormi
FamilyQwen
Downloads (HF)124
Last updated2026-09-22

Frequently asked questions about MiMo V2.6 Distill Qwen 9B Abliterated

How much VRAM does MiMo V2.6 Distill Qwen 9B Abliterated need?

About 6.0 GB at IQ3_M with an 8K context window. That is the 4.4 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 Abliterated on an 8 GB GPU?

Yes, with IQ3_M: the 4.4 GB file needs about 6.0 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 Abliterated GGUF?

It depends on the quant: IQ3_M is 4.4 GB, F16 is 17.9 GB.

What context length does MiMo V2.6 Distill Qwen 9B Abliterated 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 Abliterated GGUF?

The files are on Hugging Face in the geantendormi/MiMo-V2.6-Distill-Qwen-9B-Abliterated-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run MiMo V2.6 Distill Qwen 9B Abliterated on an RTX 3060 12GB?

Yes, the IQ3_M quant uses about 6 GB VRAM at 8 k context, leaving headroom on a 12 GB GPU.

Does the model support vision inputs?

No, the model has no vision capability.

Is the model a mixture of experts?

No, it is not a mixture of experts.

Similar models

Browse all →

More from geantendormi

All by geantendormi →

More Qwen models

All Qwen →

Other small models

All small models →