MI

XiaomiMiMo.MiMo V2.5

MimoGGUF by DevQuasarUpdated 2026-05-16
Download on Hugging Face
Parameters310B
Context1024K
Layers51
Architecturemimo2
Smallest quant113.3 GB
Quick answer

XiaomiMiMo.MiMo V2.5 needs about 204.3 GB of memory at Q4_K_M (a 186.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 113.3 GB (Q2_K) to 329.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 68.5 GB.

XiaomiMiMo.MiMo V2.5 is a 310B-parameter Mimo model in GGUF format, quantized by DevQuasar. Its trained context length is 1024K tokens. The repository has 6 quant files, from 113.3 GB (Q2_K) to 329.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K113.3 GB (8 parts) 130.9 GB
Too big Get file →
Q3_K_M148.2 GB (10 parts) 165.8 GB
Too big Get file →
Q4_K_M186.7 GB (12 parts) 204.3 GB
Too big Get file →
Q5_K_M219.4 GB (15 parts) 237.1 GB
Too big Get file →
Q6_K254.3 GB (18 parts) 271.9 GB
Too big Get file →
Q8_0329.3 GB (24 parts) 346.9 GB
Too big Get file →

What GPU do you need for XiaomiMiMo.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 XiaomiMiMo.MiMo V2.5 quant should you choose?

Q4_K_M is the usual starting point for XiaomiMiMo.MiMo V2.5: it balances file size and quality well. Here it is a 186.7 GB file.

The Q8_0 file is 329.3 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 Q2_K at 113.3 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

Architecturemimo2
Parameters310B (approximate, mixture of experts)
Layers51
Trained context1,048,576 tokens
KV cache (fp16)2040 KB per token

Source

Quantized byDevQuasar
FamilyMimo
Licensemit
Downloads (HF)330
Last updated2026-05-16

Frequently asked questions about XiaomiMiMo.MiMo V2.5

How much VRAM does XiaomiMiMo.MiMo V2.5 need?

About 204.3 GB at Q4_K_M with an 8K context window. That is the 186.7 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 XiaomiMiMo.MiMo V2.5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 130.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of XiaomiMiMo.MiMo V2.5 GGUF?

It depends on the quant: Q2_K is 113.3 GB, Q3_K_M is 148.2 GB, Q4_K_M is 186.7 GB, Q5_K_M is 219.4 GB, Q6_K is 254.3 GB, Q8_0 is 329.3 GB.

What context length does XiaomiMiMo.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 XiaomiMiMo.MiMo V2.5 GGUF?

The files are on Hugging Face in the DevQuasar/XiaomiMiMo.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 XiaomiMiMo.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.

Other GGUFs of MiMo-V2.5

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Mimo models

All Mimo →

Other large models

All large models →