Mimo-V2-Flash needs about 203.4 GB of memory at Q4_K_M (a 186.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 77.7 GB (TQ1_0) to 617.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 64.4 GB.
MiMo‑V2‑Flash: 309B MoE model with 15B active params and 256k context
MiMo‑V2‑Flash is a Mixture‑of‑Experts language model with 309 billion total parameters and 15 billion active parameters. It supports up to 256 k token context and is optimized for high‑speed reasoning and agentic workflows.
Good at
- Large context handling up to 256k tokens
- Efficient inference with hybrid attention
- Fast output via Multi‑Token Prediction
Limits
- Requires 256k context support only
- Large memory footprint for full precision
- No vision or audio capabilities
Best for
- Long‑form document summarization
- Complex reasoning tasks
- Agentic workflow orchestration
Who it’s for. Developers needing a high‑capacity MoE model for long‑context reasoning. Suitable for research and production environments with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 77.7 GB | 94.3 GB | Too big | Get file → | |
| IQ1_S | 87.2 GB (2 parts) | 103.8 GB | Too big | Get file → | |
| IQ1_M | 93.8 GB (2 parts) | 110.4 GB | Too big | Get file → | |
| IQ2_XXS | 101.6 GB (3 parts) | 118.2 GB | Too big | Get file → | |
| IQ2_M | 106.7 GB (3 parts) | 123.3 GB | Too big | Get file → | |
| Q2_K | 112.3 GB (3 parts) | 128.9 GB | Too big | Get file → | |
| Q2_K_L | 112.4 GB (3 parts) | 129.0 GB | Too big | Get file → | |
| Q2_K_XL | 116.3 GB (3 parts) | 132.9 GB | Too big | Get file → | |
| IQ3_XXS | 127.5 GB (3 parts) | 144.1 GB | Too big | Get file → | |
| Q3_K_S | 133.1 GB (3 parts) | 149.7 GB | Too big | Get file → | |
| Q3_K_XL | 137.1 GB (3 parts) | 153.7 GB | Too big | Get file → | |
| Q3_K_M | 147.3 GB (3 parts) | 163.9 GB | Too big | Get file → | |
| IQ4_XS | 164.4 GB (4 parts) | 181.1 GB | Too big | Get file → | |
| IQ4_NL | 174.0 GB (4 parts) | 190.7 GB | Too big | Get file → | |
| Q4_0 | 174.7 GB (4 parts) | 191.3 GB | Too big | Get file → | |
| Q4_K_S | 175.4 GB (4 parts) | 192.0 GB | Too big | Get file → | |
| Q4_K_XL | 177.7 GB (4 parts) | 194.3 GB | Too big | Get file → | |
| Q4_K_M | 186.8 GB (4 parts) | 203.4 GB | Too big | Get file → | |
| Q4_1 | 193.3 GB (4 parts) | 209.9 GB | Too big | Get file → | |
| Q5_K_S | 212.5 GB (5 parts) | 229.1 GB | Too big | Get file → | |
| Q5_K_M | 219.1 GB (5 parts) | 235.7 GB | Too big | Get file → | |
| Q5_K_XL | 219.8 GB (5 parts) | 236.4 GB | Too big | Get file → | |
| Q6_K | 253.5 GB (6 parts) | 270.1 GB | Too big | Get file → | |
| Q6_K_XL | 263.3 GB (6 parts) | 280.0 GB | Too big | Get file → | |
| Q8_0 | 328.2 GB (7 parts) | 344.8 GB | Too big | Get file → | |
| Q8_K_XL | 354.2 GB (8 parts) | 370.8 GB | Too big | Get file → | |
| BF16 | 617.7 GB (13 parts) | 634.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (≈192 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (≈203 GB). For 24 GB VRAM, Q5_K_S (≈229 GB). Memory estimates are approximate.
What GPU do you need for Mimo-V2-Flash?
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-Flash quant should you choose?
Q4_K_M is the usual starting point for Mimo-V2-Flash: it balances file size and quality well. Here it is a 186.8 GB file.
The Q8_0 file is 328.2 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is TQ1_0 at 77.7 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mimo-V2-Flash
How much VRAM does Mimo-V2-Flash need?
About 203.4 GB at Q4_K_M with an 8K context window. That is the 186.8 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-Flash on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 94.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mimo-V2-Flash GGUF?
It depends on the quant: TQ1_0 is 77.7 GB, IQ1_S is 87.2 GB, IQ1_M is 93.8 GB, IQ2_XXS is 101.6 GB, IQ2_M is 106.7 GB, Q2_K is 112.3 GB and 21 more.
What context length does Mimo-V2-Flash support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 16.1 GB at 8K and 64.4 GB at 32K.
Where can I download Mimo-V2-Flash GGUF?
The files are on Hugging Face in the unsloth/MiMo-V2-Flash-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-Flash 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‑Flash on 8 GB VRAM?
Use the Q4_K_S quantized file; it requires roughly 192 GB memory at 8k context, which is beyond 8 GB VRAM, so it is not feasible.
Does MiMo‑V2‑Flash support vision or audio?
No, the model only handles text; it has no vision or audio capabilities.
What is the maximum context length of MiMo‑V2‑Flash?
The model supports up to 256,000 tokens in context.