MiMo V2.6 Flash RL needs about 2.9 GB of memory at Q8_0 (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.2 GB (Q8_0) to 98.7 GB (IQ2_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
MiMo V2.6 Flash RL – 310B parameter model with 1M token context
MiMo V2.6 Flash RL is a 310B parameter model built for reinforcement learning self‑improvement. It supports reasoning and tool usage and offers a 1,048,576 token context window. The model is released under the MIT license.
Good at
- Reasoning
- Tool usage
- Long‑horizon tasks
Limits
- No vision or audio encoders included
- Large VRAM required for full model
- No separate vision support
Best for
- Agentic task planning
- Long‑form reasoning
- Tool‑integrated workflows
Who it’s for. Developers building reinforcement‑learning agents that need extensive context and tool integration. The model is suitable for research and production environments with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 2.2 GB | 2.9 GB | Fits | Get file → | |
| IQ2_XS | 98.7 GB (10 parts) | 99.4 GB | Too big | Get file → |
For systems with 8–12 GB VRAM, use the Q8_0 quantization (2.23 GB file, ~2.9 GB memory at 8 k context). For larger memory budgets, the IQ2_XS quant (98.69 GB file, ~99.4 GB memory) provides the full‑precision experience but requires a DGX‑style GPU with ~128 GB unified memory.
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: the best quant that fits is Q8_0 (2.2 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 2.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 2.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 2.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 2.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 2.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 2.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 2.9 GB in use).
Which MiMo V2.6 Flash RL quant should you choose?
Q8_0 (2.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiMo V2.6 Flash RL
How much VRAM does MiMo V2.6 Flash RL need?
About 2.9 GB at Q8_0 with an 8K context window. That is the 2.2 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?
Yes, with Q8_0: the 2.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiMo V2.6 Flash RL GGUF?
It depends on the quant: Q8_0 is 2.2 GB, IQ2_XS is 98.7 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 0.2 GB at 8K and 0.7 GB at 32K.
Where can I download MiMo V2.6 Flash RL GGUF?
The files are on Hugging Face in the TrevorJS/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 8 GB VRAM?
The Q8_0 quantization requires about 2.9 GB memory at 8 k context, so it can run on 8 GB VRAM with headroom for other processes.
Does the model support image or audio input?
No. The vision and audio encoders are not included in the GGUF files and must be provided separately.
What license applies to this model?
The model is released under the MIT license, allowing free use and modification.