MI

MiniMax M2.5 HF

MinimaxGGUF by ox-oxUpdated 2026-02-13
Download on Hugging Face
Parameters229B
Context192K
Layers62
Architectureminimax-m2
Smallest quant118.4 GB
Quick answer

MiniMax M2.5 HF 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 2 quants, from 118.4 GB (Q3_K_L) to 138.3 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

MiniMax M2.5 HF is a 229B-parameter Minimax model in GGUF format, quantized by ox-ox. Its trained context length is 192K tokens. The repository has 2 quant files, from 118.4 GB (Q3_K_L) to 138.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L118.4 GB 120.9 GB
Too big Get file →
Q4_K_M138.3 GB 140.9 GB
Too big Get file →

What GPU do you need for MiniMax M2.5 HF?

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 HF quant should you choose?

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

If memory is tight, the smallest file is Q3_K_L at 118.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byox-ox
FamilyMinimax
Licensemit
Downloads (HF)126
Last updated2026-02-13

Frequently asked questions about MiniMax M2.5 HF

How much VRAM does MiniMax M2.5 HF 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 HF on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 120.9 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q3_K_L is 118.4 GB, Q4_K_M is 138.3 GB.

What context length does MiniMax M2.5 HF 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 HF GGUF?

The files are on Hugging Face in the ox-ox/MiniMax-M2.5-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 MiniMax M2.5 HF 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 MiniMax-M2.5

Similar models

Browse all →

More from ox-ox

All by ox-ox →

More Minimax models

All Minimax →

Other large models

All large models →