MI

MiMo Ornith 9B AGSI Abliterated HQ

MimoGGUF by OliviaRossiUpdated 2026-09-29
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant6.5 GB
Quick answer

MiMo Ornith 9B AGSI Abliterated HQ needs about 8.0 GB of memory at Q5_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MiMo Ornith 9B AGSI Abliterated HQ – a 9.7B parameter reasoning and agentic hybrid model

MiMo Ornith 9B AGSI Abliterated HQ is a 9.7B parameter hybrid model built from Qwen 3.5 and Ornith 1.5. It offers high‑precision reasoning and autonomous tool use while eliminating refusal boundaries. The model is released under the Apache‑2.0 license and is fully compatible with llama.cpp, LM Studio, and Ollama.

Good at

  • High‑precision reasoning
  • Agentic tool invocation
  • Chain‑of‑thought distillation

Limits

  • No vision support
  • Requires 8k context for full memory usage
  • Only Q5_K_M quant available

Best for

  • Complex reasoning tasks
  • Autonomous terminal execution
  • Multi‑step tool calling

Who it’s for. Developers and researchers needing a large, uncensored reasoning model with agentic capabilities. The model is ideal for building AI agents that require chain‑of‑thought reasoning and tool use without refusal constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M6.5 GB 8.0 GB
Too big Get file →

For 8GB VRAM, use the Q5_K_M quant (6.47 GB file, ~8 GB memory at 8k context). If more VRAM is available, consider higher‑precision quants such as Q8_0 for better accuracy. The memory estimate is approximate.

What GPU do you need for MiMo Ornith 9B AGSI Abliterated HQ?

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).

Which MiMo Ornith 9B AGSI Abliterated HQ quant should you choose?

Q5_K_M (6.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

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 byOliviaRossi
FamilyMimo
Licenseapache-2.0
Downloads (HF)2,018
Last updated2026-09-29

Frequently asked questions about MiMo Ornith 9B AGSI Abliterated HQ

How much VRAM does MiMo Ornith 9B AGSI Abliterated HQ need?

About 8.0 GB at Q5_K_M with an 8K context window. That is the 6.5 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 Ornith 9B AGSI Abliterated HQ 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 Ornith 9B AGSI Abliterated HQ GGUF?

It depends on the quant: Q5_K_M is 6.5 GB.

What context length does MiMo Ornith 9B AGSI Abliterated HQ 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 Ornith 9B AGSI Abliterated HQ GGUF?

The files are on Hugging Face in the OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated-HQ-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 Ornith 9B AGSI Abliterated HQ use?

Hugging Face lists the license as apache-2.0. 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 Ornith 9B on 8GB VRAM?

Yes, the Q5_K_M quant uses about 8 GB of VRAM at an 8k context length, which fits within an 8 GB budget.

Does the model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of MiMo-Ornith-9B-AGSI-Abliterated-HQ

Similar models

Browse all →

More from OliviaRossi

All by OliviaRossi →

More Mimo models

All Mimo →

Other small models

All small models →