MiMo V2.6 Flash RL NVFP4 needs about 4.9 GB of memory at BF16 (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.2 GB (BF16) to 192.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
MiMo V2.6 Flash RL NVFP4 – 310B coding‑focused model
MiMo V2.6 Flash RL NVFP4 is a 310‑billion‑parameter model optimized for reinforcement learning and coding tasks. It supports up to 1,048,576 context tokens and is released under the MIT license. The model is available in BF16 and a large‑scale unknown quantization.
Good at
- Coding tasks
- Reinforcement learning
- Long‑context generation
Limits
- No vision or audio support
- Requires large VRAM for full model
- Large memory footprint for unknown quant
Best for
- Developers building coding assistants
- Researchers fine‑tuning RL agents
- Teams needing long‑context generation
Who it’s for. The model is suited for developers and researchers who need a large, coding‑centric LLM with reinforcement learning capabilities. It is ideal for teams that can allocate sufficient GPU memory and want to experiment with RL fine‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 4.2 GB | 4.9 GB | Fits | Get file → | |
| — | 192.0 GB (10 parts) | 192.7 GB | Too big | Get file → |
For 8 GB VRAM, use the BF16 quantization (4.19 GB file, ~4.9 GB memory at 8 k context). The unknown quant is 191.99 GB and requires ~192.7 GB memory, so it is only suitable for very large GPU setups.
What GPU do you need for MiMo V2.6 Flash RL NVFP4?
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 BF16 (4.2 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.9 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.9 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.9 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.9 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.9 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (4.2 GB file, about 4.9 GB in use).
Which MiMo V2.6 Flash RL NVFP4 quant should you choose?
BF16 (4.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiMo V2.6 Flash RL NVFP4
How much VRAM does MiMo V2.6 Flash RL NVFP4 need?
About 4.9 GB at BF16 with an 8K context window. That is the 4.2 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 NVFP4 on an 8 GB GPU?
Yes, with BF16: the 4.2 GB file needs about 4.9 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 NVFP4 GGUF?
It depends on the quant: BF16 is 4.2 GB, file is 192.0 GB.
What context length does MiMo V2.6 Flash RL NVFP4 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 NVFP4 GGUF?
The files are on Hugging Face in the ProCreations/MiMo-V2.6-Flash-RL-NVFP4 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 NVFP4 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?
Yes, the BF16 quantization uses about 4.9 GB of VRAM at 8 k context, which fits within 8 GB. The unknown quant is too large for this budget.
Is the model compatible with CPU inference?
CPU inference is possible, but the large memory requirement (≈4.9 GB for BF16) may exceed typical CPU RAM limits. Use a GPU for efficient performance.
Does the model support vision or audio inputs?
No, the released model does not provide vision or audio capabilities. It is focused on text and coding tasks.