MI

MiniMax M2

MinimaxGGUF by bartowskiUpdated 2025-11-01
Download on Hugging Face
Parameters230B
Context192K
Layers62
Architectureminimax-m2
Smallest quant0.5 GB
Quick answer

MiniMax M2 needs about 141.2 GB of memory at Q4_K_M (a 138.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.5 GB to 243.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

MiniMax M2 – a 230B total, 10B active parameter 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 complex tool‑chain agentic workflows. The model is released under the MIT license and supports 196 608‑token context.

Good at

  • Advanced coding and multi‑file edits
  • Complex agentic tool use
  • High‑throughput interactive tasks

Limits

  • No vision support
  • Requires large VRAM for higher‑quality quants
  • Limited to 196 608 context tokens

Best for

  • Developers building terminal‑based tools
  • Agents performing web browsing and code execution
  • Batch sampling for CI pipelines

Who it’s for. Engineers and researchers needing a compact, high‑performance model for coding and agentic workflows. The model is suitable for deployment on systems with sufficient VRAM to accommodate the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 3.1 GB
Fits Get file →
IQ1_S47.0 GB 49.6 GB
Too big Get file →
IQ1_M49.0 GB 51.6 GB
Too big Get file →
IQ2_XXS54.7 GB (2 parts) 57.3 GB
Too big Get file →
IQ2_XS63.1 GB (2 parts) 65.7 GB
Too big Get file →
IQ2_S63.4 GB (2 parts) 65.9 GB
Too big Get file →
IQ2_M72.0 GB (2 parts) 74.6 GB
Too big Get file →
Q2_K79.8 GB (2 parts) 82.4 GB
Too big Get file →
Q2_K_L80.4 GB (3 parts) 83.0 GB
Too big Get file →
IQ3_XXS90.1 GB (3 parts) 92.7 GB
Too big Get file →
IQ3_XS93.8 GB (3 parts) 96.3 GB
Too big Get file →
Q3_K_S99.1 GB (3 parts) 101.7 GB
Too big Get file →
IQ3_M104.0 GB (3 parts) 106.5 GB
Too big Get file →
Q3_K_M104.0 GB (3 parts) 106.5 GB
Too big Get file →
Q3_K_L108.2 GB (3 parts) 110.8 GB
Too big Get file →
Q3_K_XL108.7 GB (3 parts) 111.3 GB
Too big Get file →
IQ4_XS122.2 GB (4 parts) 124.7 GB
Too big Get file →
IQ4_NL129.2 GB (4 parts) 131.8 GB
Too big Get file →
Q4_0131.3 GB (4 parts) 133.9 GB
Too big Get file →
Q4_K_S133.8 GB (4 parts) 136.3 GB
Too big Get file →
Q4_K_M138.6 GB (4 parts) 141.2 GB
Too big Get file →
Q4_1143.3 GB (4 parts) 145.9 GB
Too big Get file →
Q5_K_S157.6 GB (4 parts) 160.1 GB
Too big Get file →
Q5_K_M162.4 GB (5 parts) 165.0 GB
Too big Get file →
Q6_K187.8 GB (5 parts) 190.4 GB
Too big Get file →
Q8_0243.1 GB (7 parts) 245.7 GB
Too big Get file →

For 8 GB VRAM, use the IQ1_S quant (file size 47.01 GB, ~49.6 GB memory at 8 k context). For 16 GB VRAM, IQ2_XS (63.14 GB, ~65.7 GB memory) or Q2_K (79.82 GB, ~82.4 GB memory) are suitable. Higher VRAM allows larger quants such as Q4_K_M (138.59 GB, ~141.2 GB memory).

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: 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 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 138.6 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 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
Parameters230B (approximate, mixture of experts)
Layers62
Trained context196,608 tokens
KV cache (fp16)248 KB per token

Source

Quantized bybartowski
FamilyMinimax
Licensemit
Downloads (HF)1,302
Last updated2025-11-01

Frequently asked questions about MiniMax M2

How much VRAM does MiniMax M2 need?

About 141.2 GB at Q4_K_M with an 8K context window. That is the 138.6 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 MiniMax M2 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 GGUF?

It depends on the quant: file is 0.5 GB, IQ1_S is 47.0 GB, IQ1_M is 49.0 GB, IQ2_XXS is 54.7 GB, IQ2_XS is 63.1 GB, IQ2_S is 63.4 GB and 20 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 bartowski/MiniMaxAI_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?

Yes, the IQ1_S quant uses about 49.6 GB of memory at 8 k context, which fits within 8 GB VRAM when using efficient batching.

Does MiniMax M2 support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of MiniMax-M2

Similar models

Browse all →

More from bartowski

All by bartowski →

More Minimax models

All Minimax →

Other large models

All large models →