MI

Minimax-M2.5

MinimaxGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters229B
Context192K
Layers62
Architectureminimax-m2
Smallest quant85.9 GB
Quick answer

Minimax-M2.5 needs about 141.5 GB of memory at its main file (a 139.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 85.9 GB to 165.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

MiniMax-M2.5: a large Mixture-of-Experts model for coding, agentic tasks and multilingual work

MiniMax-M2.5 is a 229‑billion‑parameter Mixture-of-Experts model trained on 196,608 context tokens. It is optimized for coding, agentic tool use, and multilingual tasks. The model is available in several APEX quantizations.

Good at

  • Coding across 10+ languages
  • Agentic tool use and search
  • Multilingual reasoning

Limits

  • Large context requires high VRAM
  • No vision support
  • License is other

Best for

  • Full‑stack code generation
  • Agentic workflow automation
  • Multilingual document processing

Who it’s for. Developers and researchers needing a high‑capacity model for coding and agentic applications. The model is suitable for users with sufficient GPU memory to run the large quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—85.9 GB 88.5 GB
Too big Get file →
—107.1 GB 109.7 GB
Too big Get file →
—107.1 GB 109.7 GB
Too big Get file →
—139.0 GB 141.5 GB
Too big Get file →
—139.0 GB 141.5 GB
Too big Get file →
—165.9 GB 168.4 GB
Too big Get file →
—165.9 GB 168.4 GB
Too big Get file →

For 8 GB VRAM, use the 85.9 GB file; it estimates 88.5 GB memory at 8 k context. For 16 GB VRAM, the 107.09 GB file uses about 109.7 GB memory. Larger VRAM allows the 138.95 GB or 165.86 GB files, which estimate 141.5 GB and 168.4 GB respectively. Memory estimates are approximate.

What GPU do you need for Minimax-M2.5?

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 Minimax-M2.5 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 85.9 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

Architectureminimax-m2
Parameters229B (approximate, mixture of experts)
Layers62
Trained context196,608 tokens
KV cache (fp16)248 KB per token

Source

Quantized bymudler
FamilyMinimax
Licenseother
Downloads (HF)1,830
Last updated2026-08-17

Frequently asked questions about Minimax-M2.5

How much VRAM does Minimax-M2.5 need?

About 141.5 GB at its main file with an 8K context window. That is the 139.0 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 Minimax-M2.5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 88.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Minimax-M2.5 GGUF?

It depends on the quant: file is 85.9 GB, file is 107.1 GB, file is 107.1 GB, file is 139.0 GB, file is 139.0 GB, file is 165.9 GB and 1 more.

What context length does Minimax-M2.5 support?

The GGUF header lists a trained context length of 196,608 tokens (192K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.3 GB at 32K.

Where can I download Minimax-M2.5 GGUF?

The files are on Hugging Face in the mudler/MiniMax-M2.5-APEX-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 Minimax-M2.5 use?

Hugging Face lists the license as other. 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 MiniMax-M2.5 on 8 GB VRAM?

The smallest file is 85.9 GB, estimating 88.5 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does MiniMax-M2.5 support vision tasks?

No, the model has no vision support.

What license applies to MiniMax-M2.5?

The model is released under an other license.

Other GGUFs of MiniMax-M2.5

Similar models

Browse all →

More from mudler

All by mudler →

More Minimax models

All Minimax →

Other large models

All large models →