MI

Minimax-M2

MinimaxGGUF by unslothUpdated 2025-11-03
Download on Hugging Face
Parameters230B
Context192K
Layers62
Architectureminimax-m2
Smallest quant56.4 GB
Quick answer

Minimax-M2 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 27 quants, from 56.4 GB (TQ1_0) to 457.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

MiniMax-M2 – 230 B total parameters, 10 B active, MoE model for coding and agentic tasks

MiniMax-M2 is a 230 billion‑parameter MoE model with 10 billion active parameters. It is optimized for coding, multi‑file edits, and agentic tool use. The model is released under the MIT license and supports up to 196 608 context tokens.

Good at

  • Advanced coding workflows
  • Agentic tool chaining
  • High‑throughput interactive use

Limits

  • Large VRAM requirement for high‑quality quants
  • No vision support
  • Requires 8 k context for memory estimates

Best for

  • Developer tool integration
  • Automated code repair
  • Complex agentic pipelines

Who it’s for. Engineers and researchers needing a compact yet powerful model for coding and agentic applications. The model is suitable for deployment in environments where 10 billion active parameters provide sufficient performance without the full 230 billion parameter load.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_056.4 GB 59.0 GB
Too big Get file →
IQ1_S64.0 GB (2 parts) 66.6 GB
Too big Get file →
IQ1_M68.7 GB (2 parts) 71.3 GB
Too big Get file →
IQ2_XXS74.0 GB (2 parts) 76.6 GB
Too big Get file →
IQ2_M78.1 GB (2 parts) 80.7 GB
Too big Get file →
Q2_K83.3 GB (2 parts) 85.9 GB
Too big Get file →
Q2_K_L83.4 GB (2 parts) 86.0 GB
Too big Get file →
Q2_K_XL85.8 GB (2 parts) 88.3 GB
Too big Get file →
IQ3_XXS93.6 GB (2 parts) 96.2 GB
Too big Get file →
Q3_K_S98.7 GB (2 parts) 101.3 GB
Too big Get file →
Q3_K_XL101.5 GB (3 parts) 104.0 GB
Too big Get file →
Q3_K_M109.3 GB (3 parts) 111.9 GB
Too big Get file →
IQ4_XS121.9 GB (3 parts) 124.5 GB
Too big Get file →
IQ4_NL129.0 GB (3 parts) 131.6 GB
Too big Get file →
Q4_0129.5 GB (3 parts) 132.1 GB
Too big Get file →
Q4_K_S130.0 GB (3 parts) 132.6 GB
Too big Get file →
Q4_K_XL131.6 GB (3 parts) 134.2 GB
Too big Get file →
Q4_K_M138.3 GB (3 parts) 140.9 GB
Too big Get file →
Q4_1143.2 GB (3 parts) 145.8 GB
Too big Get file →
Q5_K_S157.5 GB (4 parts) 160.1 GB
Too big Get file →
Q5_K_XL162.1 GB (4 parts) 164.7 GB
Too big Get file →
Q5_K_M162.3 GB (4 parts) 164.9 GB
Too big Get file →
Q6_K187.8 GB (4 parts) 190.3 GB
Too big Get file →
Q6_K_XL194.3 GB (4 parts) 196.9 GB
Too big Get file →
Q8_0243.1 GB (5 parts) 245.7 GB
Too big Get file →
Q8_K_XL261.4 GB (6 parts) 264.0 GB
Too big Get file →
BF16457.5 GB (10 parts) 460.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (≈133 GB file, 133 GB memory at 8 k context). For 16 GB VRAM, Q4_K_M (≈141 GB file, 141 GB memory). For 32 GB VRAM, Q5_K_XL (≈162 GB file, 165 GB memory). Memory estimates are approximate.

What GPU do you need for Minimax-M2?

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 quant should you choose?

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

The Q8_0 file is 243.1 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 TQ1_0 at 56.4 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureminimax-m2
Parameters230B (approximate, mixture of experts)
Layers62
Trained context196,608 tokens
KV cache (fp16)248 KB per token

Source

Quantized byunsloth
FamilyMinimax
Licensemit
Downloads (HF)9,016
Last updated2025-11-03

Frequently asked questions about Minimax-M2

How much VRAM does Minimax-M2 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 59.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Minimax-M2 GGUF?

It depends on the quant: TQ1_0 is 56.4 GB, IQ1_S is 64.0 GB, IQ1_M is 68.7 GB, IQ2_XXS is 74.0 GB, IQ2_M is 78.1 GB, Q2_K is 83.3 GB and 21 more.

What context length does Minimax-M2 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 GGUF?

The files are on Hugging Face in the unsloth/MiniMax-M2-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 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 MiniMax-M2 on 8 GB VRAM?

Use the Q4_K_S quant; it requires about 133 GB of VRAM at 8 k context, which is beyond 8 GB, so it is not feasible.

Does MiniMax-M2 support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of MiniMax-M2

Similar models

Browse all →

More from unsloth

All by unsloth →

More Minimax models

All Minimax →

Other large models

All large models →