MI

Mimo-V2.5-Pro

MimoGGUF by unslothUpdated 2026-05-11
Download on Hugging Face
Parameters1020B
Context1024K
Layers73
Architecturemimo2
Smallest quant304.1 GB
Quick answer

Mimo-V2.5-Pro needs about 679.1 GB of memory at Q4_K_M (a 629.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 22 quants, from 304.1 GB (IQ1_M) to 2046.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 196.0 GB.

MiMo‑V2.5‑Pro: 1.02T‑parameter MoE model with 1M‑token context

MiMo‑V2.5‑Pro is an open‑source Mixture‑of‑Experts language model with 1.02T total parameters and 42B active parameters. It supports up to 1M tokens of context and is optimized for long‑horizon, agentic tasks. The model uses a hybrid attention architecture and Multi‑Token Prediction to accelerate inference.

Good at

  • Long‑context reasoning up to 1M tokens
  • Complex agentic workflows
  • High‑speed inference with MTP

Limits

  • Requires large VRAM for full‑precision runs
  • No vision or audio capabilities
  • License is MIT, no commercial restrictions

Best for

  • Long‑form code generation
  • Agentic task orchestration
  • Large‑scale data analysis

Who it’s for. Developers and researchers needing a high‑capacity language model for complex, long‑horizon tasks. The model is suitable for those who can allocate sufficient GPU memory and want to experiment with MoE architectures.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M304.1 GB (8 parts) 353.6 GB
Too big Get file →
IQ2_XXS317.2 GB (8 parts) 366.6 GB
Too big Get file →
IQ2_M317.3 GB (8 parts) 366.8 GB
Too big Get file →
Q2_K_XL338.4 GB (8 parts) 387.9 GB
Too big Get file →
IQ3_S377.9 GB (9 parts) 427.4 GB
Too big Get file →
IQ3_XXS412.7 GB (10 parts) 462.1 GB
Too big Get file →
Q3_K_M459.7 GB (11 parts) 509.2 GB
Too big Get file →
Q3_K_XL459.9 GB (11 parts) 509.4 GB
Too big Get file →
IQ4_XS490.7 GB (11 parts) 540.2 GB
Too big Get file →
IQ4_NL501.3 GB (12 parts) 550.8 GB
Too big Get file →
Q4_K_S588.5 GB (14 parts) 638.0 GB
Too big Get file →
MXFP4_MOE610.5 GB (14 parts) 660.0 GB
Too big Get file →
Q4_K_M629.6 GB (15 parts) 679.1 GB
Too big Get file →
Q4_K_XL631.0 GB (15 parts) 680.5 GB
Too big Get file →
Q5_K_S713.2 GB (16 parts) 762.7 GB
Too big Get file →
Q5_K_M758.0 GB (17 parts) 807.5 GB
Too big Get file →
Q5_K_XL759.3 GB (17 parts) 808.8 GB
Too big Get file →
Q6_K846.6 GB (19 parts) 896.0 GB
Too big Get file →
Q6_K_XL928.5 GB (21 parts) 978.0 GB
Too big Get file →
Q8_01087.6 GB (24 parts) 1137.1 GB
Too big Get file →
Q8_K_XL1101.5 GB (25 parts) 1150.9 GB
Too big Get file →
BF162046.7 GB (43 parts) 2096.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M or IQ2_XXS. For 16 GB VRAM, Q4_K_M or Q4_K_XL provide a balance of size and speed. For 32 GB VRAM, Q5_K_XL or Q6_K_XL offer higher precision while staying within memory limits.

What GPU do you need for Mimo-V2.5-Pro?

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-Pro quant should you choose?

Q4_K_M is the usual starting point for Mimo-V2.5-Pro: it balances file size and quality well. Here it is a 629.6 GB file.

The Q8_0 file is 1087.6 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 IQ1_M at 304.1 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
Parameters1020B (approximate, mixture of experts)
Layers73
Trained context1,048,576 tokens
KV cache (fp16)5840 KB per token

Source

Quantized byunsloth
FamilyMimo
Licensemit
Downloads (HF)4,949
Last updated2026-05-11

Frequently asked questions about Mimo-V2.5-Pro

How much VRAM does Mimo-V2.5-Pro need?

About 679.1 GB at Q4_K_M with an 8K context window. That is the 629.6 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-Pro on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 353.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mimo-V2.5-Pro GGUF?

It depends on the quant: IQ1_M is 304.1 GB, IQ2_XXS is 317.2 GB, IQ2_M is 317.3 GB, Q2_K_XL is 338.4 GB, IQ3_S is 377.9 GB, IQ3_XXS is 412.7 GB and 16 more.

What context length does Mimo-V2.5-Pro 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 49.0 GB at 8K and 196.0 GB at 32K.

Where can I download Mimo-V2.5-Pro GGUF?

The files are on Hugging Face in the unsloth/MiMo-V2.5-Pro-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-Pro 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‑Pro on 8 GB VRAM?

Use the IQ1_M or IQ2_XXS quantized files; they fit within 8 GB VRAM with an estimated 353.6 GB memory usage at 8k context.

Does the model support vision or audio input?

No, MiMo‑V2.5‑Pro is a text‑only model and does not include vision or audio capabilities.

What is the maximum context length I can use?

The model supports up to 1M tokens of context length.

Other GGUFs of MiMo-V2.5-Pro

Similar models

Browse all →

More from unsloth

All by unsloth →

More Mimo models

All Mimo →

Other large models

All large models →