MiMO V2.5 MTP needs about 131.6 GB of memory at IQ3_S (a 114.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 85.7 GB (IQ2_XXS) to 256.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 68.5 GB.
MiMO V2.5 MTP is a 310B-parameter Mimo model in GGUF format, quantized by tnhnyzc. Its trained context length is 1024K tokens. The repository has 4 quant files, from 85.7 GB (IQ2_XXS) to 256.0 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 85.7 GB (17 parts) | 103.3 GB | Too big | Get file → | |
| IQ3_S | 114.0 GB | 131.6 GB | Too big | Get file → | |
| Q4_K | 178.0 GB (17 parts) | 195.6 GB | Too big | Get file → | |
| Q6_K | 256.0 GB (17 parts) | 273.7 GB | Too big | Get file → |
What GPU do you need for MiMO V2.5 MTP?
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 MTP quant should you choose?
IQ3_S (114.0 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.
If memory is tight, the smallest file is IQ2_XXS at 85.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiMO V2.5 MTP
How much VRAM does MiMO V2.5 MTP need?
About 131.6 GB at IQ3_S with an 8K context window. That is the 114.0 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 MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 103.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MiMO V2.5 MTP GGUF?
It depends on the quant: IQ2_XXS is 85.7 GB, IQ3_S is 114.0 GB, Q4_K is 178.0 GB, Q6_K is 256.0 GB.
What context length does MiMO V2.5 MTP 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 MTP GGUF?
The files are on Hugging Face in the tnhnyzc/MiMO-V2.5-MTP-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 MTP 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.