MiMo V2.5 needs about 129.7 GB of memory at IQ3_S (a 113.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 113.1 GB (IQ3_S) to 146.9 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 64.4 GB.
MiMo V2.5 is a 309B-parameter Mimo model in GGUF format, quantized by gghfez. Its trained context length is 1024K tokens. The repository has 2 quant files, from 113.1 GB (IQ3_S) to 146.9 GB (IQ4_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 113.1 GB (4 parts) | 129.7 GB | Too big | Get file → | |
| IQ4_XS | 146.9 GB (4 parts) | 163.5 GB | Too big | Get file → |
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: 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 V2.5 quant should you choose?
IQ3_S (113.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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 129.7 GB at IQ3_S with an 8K context window. That is the 113.1 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 129.7 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: IQ3_S is 113.1 GB, IQ4_XS is 146.9 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 16.1 GB at 8K and 64.4 GB at 32K.
Where can I download MiMo V2.5 GGUF?
The files are on Hugging Face in the gghfez/MiMo-V2.5-ikllama-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.