MI

MiniMax M2.5

MinimaxGGUF by mradermacherUpdated 2026-02-24
Download on Hugging Face
Parameters229B
Context192K
Layers62
Architectureminimax-m2
Smallest quant0.5 GB
Quick answer

MiniMax M2.5 needs about 140.9 GB of memory at Q4_K_M (a 138.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.5 GB to 187.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

MiniMax M2.5 – a 229‑billion‑parameter, reasoning and tool‑using model

MiniMax M2.5 is a 229‑billion‑parameter model trained with reinforcement learning for complex real‑world tasks. It excels in coding, agentic tool use, and search, with a trained context of 196608 tokens.

Good at

  • Coding
  • Agentic tool use
  • Reasoning

Limits

  • No vision support
  • Requires large VRAM for higher‑quality quants
  • License is other

Best for

  • Complex coding tasks
  • Agentic workflows
  • Search‑intensive applications

Who it’s for. Developers and researchers needing a large, reasoning‑capable model for agentic and coding tasks. It is suitable for those who can allocate sufficient GPU memory for the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 3.1 GB
Fits Get file →
IQ1_S46.5 GB 49.1 GB
Too big Get file →
IQ1_M51.6 GB 54.2 GB
Too big Get file →
IQ2_XXS60.1 GB 62.7 GB
Too big Get file →
IQ2_XS67.0 GB 69.5 GB
Too big Get file →
IQ2_S68.0 GB 70.6 GB
Too big Get file →
IQ2_M74.8 GB 77.4 GB
Too big Get file →
Q2_K_S77.6 GB 80.1 GB
Too big Get file →
Q2_K83.3 GB 85.9 GB
Too big Get file →
IQ3_XXS88.0 GB 90.5 GB
Too big Get file →
IQ3_XS93.3 GB 95.9 GB
Too big Get file →
Q3_K_S98.7 GB 101.3 GB
Too big Get file →
IQ3_S98.7 GB 101.3 GB
Too big Get file →
IQ3_M100.0 GB 102.6 GB
Too big Get file →
Q3_K_M109.3 GB 111.9 GB
Too big Get file →
Q3_K_L118.4 GB 120.9 GB
Too big Get file →
IQ4_XS121.9 GB 124.5 GB
Too big Get file →
Q4_0129.5 GB 132.1 GB
Too big Get file →
Q4_K_S130.0 GB 132.6 GB
Too big Get file →
Q4_K_M138.3 GB 140.9 GB
Too big Get file →
Q4_1143.2 GB 145.8 GB
Too big Get file →
Q5_K_S157.5 GB 160.1 GB
Too big Get file →
Q5_K_M162.3 GB 164.9 GB
Too big Get file →
Q6_K187.8 GB 190.3 GB
Too big Get file →

For 8 GB VRAM, use the IQ1_S quant (file size 46.51 GB, estimated 49.1 GB memory at 8 k context). For 16 GB VRAM, IQ1_M (51.61 GB, 54.2 GB memory) or Q2_K (83.3 GB, 85.9 GB memory). Higher quants require more memory.

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: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).

Which MiniMax M2.5 quant should you choose?

Q4_K_M is the usual starting point for MiniMax M2.5: it balances file size and quality well. Here it is a 138.3 GB file.

If memory is tight, the smallest file is the first one in the table at 0.5 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 bymradermacher
FamilyMinimax
Licenseother
Downloads (HF)673
Last updated2026-02-24

Frequently asked questions about MiniMax M2.5

How much VRAM does MiniMax M2.5 need?

About 140.9 GB at Q4_K_M with an 8K context window. That is the 138.3 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?

Yes, with the smaller files: the 0.5 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniMax M2.5 GGUF?

It depends on the quant: file is 0.5 GB, IQ1_S is 46.5 GB, IQ1_M is 51.6 GB, IQ2_XXS is 60.1 GB, IQ2_XS is 67.0 GB, IQ2_S is 68.0 GB and 18 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 mradermacher/MiniMax-M2.5-i1-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?

Use the IQ1_S quant; it estimates 49.1 GB memory at 8 k context, which is beyond 8 GB VRAM, so it will not fit. Lower quants are not available.

Does MiniMax M2.5 support vision tasks?

No, the model does not support vision.

What is the context length of MiniMax M2.5?

The trained context length is 196608 tokens.

Other GGUFs of MiniMax-M2.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Minimax models

All Minimax →

Other large models

All large models →