MI

MiMo-V2.6-Flash-RL

MimoGGUF by YanissAmzUpdated 2026-09-23
Download on Hugging Face
Parameters310B
Context1024K
Layers51
Architecturemimo2
Smallest quant107.8 GB
Quick answer

MiMo-V2.6-Flash-RL needs about 125.5 GB of memory at IQ2_M (a 107.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 68.5 GB.

MiMo-V2.6-Flash-RL: 320B MiMo model with 1M token context, RL‑trained, single‑quant GGUF

MiMo‑V2.6‑Flash‑RL is a 320‑billion‑parameter MiMo model trained with reinforcement learning for self‑improvement. It supports 1,048,576‑token context and is distributed as a single IQ2_M GGUF file. The model is released under the MIT license and can run on any llama.cpp build.

Good at

  • Large‑context reasoning up to 1M tokens
  • Reinforcement‑learning‑derived task performance
  • Omnimodal capabilities (text, image, video, audio)

Limits

  • Requires ~128 GB unified memory to load the IQ2_M GGUF
  • No vision support in the provided quant
  • Only one quant available (IQ2_M)

Best for

  • Long‑form document analysis
  • Agentic task execution with RL‑trained policies
  • Multi‑modal content generation

Who it’s for. Developers and researchers needing a high‑capacity RL‑trained MiMo model for long‑horizon tasks. The model is suitable for environments with large unified memory and llama.cpp compatibility.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M107.8 GB (3 parts) 125.5 GB
Too big Get file →

The IQ2_M quant is 107.84 GB and needs about 125.5 GB of RAM/VRAM at 8 k context. It is suitable for systems with ~128 GB of unified memory. No other quants are provided, so this is the only option to run the model.

What GPU do you need for MiMo-V2.6-Flash-RL?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which MiMo-V2.6-Flash-RL quant should you choose?

IQ2_M (107.8 GB) is the middle option in this repository. 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

Architecturemimo2
Parameters310B (approximate, mixture of experts)
Layers51
Trained context1,048,576 tokens
KV cache (fp16)2040 KB per token

Source

Quantized byYanissAmz
FamilyMimo
Licensemit
Downloads (HF)12,874
Last updated2026-09-23

Frequently asked questions about MiMo-V2.6-Flash-RL

How much VRAM does MiMo-V2.6-Flash-RL need?

About 125.5 GB at IQ2_M with an 8K context window. That is the 107.8 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-Flash-RL on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 125.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MiMo-V2.6-Flash-RL GGUF?

It depends on the quant: IQ2_M is 107.8 GB.

What context length does MiMo-V2.6-Flash-RL support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 17.1 GB at 8K and 68.5 GB at 32K.

Where can I download MiMo-V2.6-Flash-RL GGUF?

The files are on Hugging Face in the YanissAmz/MiMo-V2.6-Flash-RL-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-Flash-RL 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‑Flash‑RL on a machine with 8 GB VRAM?

No. The IQ2_M GGUF requires roughly 125.5 GB of memory at 8 k context, far beyond 8 GB VRAM.

Is there a quant that fits on a 64 GB machine?

No, the only provided quant is IQ2_M, which needs about 128 GB of unified memory.

Other GGUFs of MiMo-V2.6-Flash-RL

Similar models

Browse all →

More from YanissAmz

All by YanissAmz →

More Mimo models

All Mimo →

Other large models

All large models →