MiMo V2.5 needs about 208.4 GB of memory at Q4_K_M (a 190.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 0.5 GB to 329.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 68.5 GB.
MiMo V2.5 – a multimodal LLM with reasoning, tools, and vision
MiMo V2.5 is a native omnimodal model built on the mimo2 architecture. It supports text, image, video, and audio understanding with a 1,048,576 token context window. The model is released under the MIT license.
Good at
- Long‑context reasoning
- Multimodal perception
- Agentic workflows
Limits
- No explicit vision support in current branch
- Large VRAM requirement for higher quants
- Requires updated config files
Best for
- Chatbots needing multimodal input
- Research on multimodal LLMs
- Developers building agentic applications
Who it’s for. The model is suitable for developers and researchers who need a unified architecture for text, image, video, and audio tasks. It is ideal for those who can manage the memory demands and keep the repository up to date.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 18.1 GB | Too big | Get file → | |
| IQ3_S | 114.2 GB (4 parts) | 131.8 GB | Too big | Get file → | |
| IQ4_XS | 147.9 GB (4 parts) | 165.5 GB | Too big | Get file → | |
| Q4_K_M | 190.8 GB (5 parts) | 208.4 GB | Too big | Get file → | |
| Q5_K_M | 229.1 GB (6 parts) | 246.7 GB | Too big | Get file → | |
| Q8_0 | 329.3 GB (8 parts) | 346.9 GB | Too big | Get file → |
For 8 GB VRAM, the IQ3_S quant (~114.15 GB file) is the most feasible, estimating 131.8 GB memory at 8 k context. If you have 16 GB VRAM, consider Q4_XS (~147.92 GB file) with an estimate of 165.5 GB. Higher quants like Q5_K_M or Q8_0 require more than 32 GB VRAM and are not recommended for low‑budget setups.
What GPU do you need for MiMo V2.5?
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: the best quant that fits is the main file (0.5 GB file, about 18.1 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 18.1 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 18.1 GB in use).
Which MiMo V2.5 quant should you choose?
Q4_K_M is the usual starting point for MiMo V2.5: it balances file size and quality well. Here it is a 190.8 GB file.
The Q8_0 file is 329.3 GB, about 1.7 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 the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiMo V2.5
How much VRAM does MiMo V2.5 need?
About 208.4 GB at Q4_K_M with an 8K context window. That is the 190.8 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 V2.5 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MiMo V2.5 GGUF?
It depends on the quant: file is 0.5 GB, IQ3_S is 114.2 GB, IQ4_XS is 147.9 GB, Q4_K_M is 190.8 GB, Q5_K_M is 229.1 GB, Q8_0 is 329.3 GB.
What context length does MiMo V2.5 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 V2.5 GGUF?
The files are on Hugging Face in the QuantPasture/MiMo-V2.5-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 V2.5 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 V2.5 on 8 GB VRAM?
The smallest quant, IQ3_S, estimates 131.8 GB memory at 8 k context, so 8 GB VRAM is insufficient.
What is the maximum context length of MiMo V2.5?
The model supports 1,048,576 tokens of context.
Is MiMo V2.5 licensed for commercial use?
It is released under the MIT license, which permits commercial use.