MI

MiniMax M2.1 REAP 30

MinimaxGGUF by mradermacherUpdated 2026-06-22
Download on Hugging Face
Parameters162B
Context192K
Layers62
Architectureminimax-m2
Smallest quant0.3 GB
Quick answer

MiniMax M2.1 REAP 30 needs about 100.6 GB of memory at Q4_K_M (a 98.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.3 GB to 133.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.

MiniMax M2.1 REAP 30 – 162B parameter model with expert pruning

MiniMax M2.1 REAP 30 is a 162B parameter model that uses REAP pruning to reduce expert usage. It supports reasoning and tool usage. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Reasoning tasks
  • Tool integration
  • Long‑context handling

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is Apache‑2.0

Best for

  • Chatbot development
  • Code generation
  • Complex question answering

Who it’s for. Developers building AI assistants that need reasoning and tool use. Researchers wanting a large, pruned model for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.3 GB 2.9 GB
Fits Get file →
IQ1_S33.1 GB 35.7 GB
Too big Get file →
IQ1_M36.7 GB 39.3 GB
Too big Get file →
IQ2_XXS42.7 GB 45.3 GB
Too big Get file →
IQ2_XS47.5 GB 50.1 GB
Too big Get file →
IQ2_S48.3 GB 50.9 GB
Too big Get file →
IQ2_M53.1 GB 55.7 GB
Too big Get file →
Q2_K_S55.0 GB 57.6 GB
Too big Get file →
Q2_K59.1 GB 61.7 GB
Too big Get file →
IQ3_XXS62.4 GB 64.9 GB
Too big Get file →
IQ3_XS66.2 GB 68.8 GB
Too big Get file →
Q3_K_S70.0 GB 72.6 GB
Too big Get file →
IQ3_S70.0 GB 72.6 GB
Too big Get file →
IQ3_M70.9 GB 73.5 GB
Too big Get file →
Q3_K_M77.5 GB 80.0 GB
Too big Get file →
Q3_K_L83.9 GB 86.5 GB
Too big Get file →
IQ4_XS86.4 GB 89.0 GB
Too big Get file →
Q4_091.8 GB 94.3 GB
Too big Get file →
Q4_K_S92.1 GB 94.7 GB
Too big Get file →
Q4_K_M98.0 GB 100.6 GB
Too big Get file →
Q4_1101.5 GB 104.1 GB
Too big Get file →
Q5_K_S111.6 GB 114.1 GB
Too big Get file →
Q5_K_M115.0 GB 117.5 GB
Too big Get file →
Q6_K133.0 GB 135.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 33.1 GB, estimated 35.7 GB memory). For 16 GB VRAM, IQ2_XS (47.51 GB, 50.1 GB memory) or Q2_K (59.1 GB, 61.7 GB memory). For 24 GB VRAM, Q3_K_M (77.47 GB, 80 GB memory) or Q4_K_M (97.99 GB, 100.6 GB memory). Estimates are approximate.

What GPU do you need for MiniMax M2.1 REAP 30?

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 (0.3 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.9 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.9 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.9 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.9 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.9 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_XXS (42.7 GB file, about 45.3 GB in use).

Which MiniMax M2.1 REAP 30 quant should you choose?

Q4_K_M is the usual starting point for MiniMax M2.1 REAP 30: it balances file size and quality well. Here it is a 98.0 GB file.

If memory is tight, the smallest file is the first one in the table at 0.3 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
Parameters162B (approximate, mixture of experts)
Layers62
Trained context196,608 tokens
KV cache (fp16)248 KB per token

Source

Quantized bymradermacher
FamilyMinimax
Licenseapache-2.0
Downloads (HF)985
Last updated2026-06-22

Frequently asked questions about MiniMax M2.1 REAP 30

How much VRAM does MiniMax M2.1 REAP 30 need?

About 100.6 GB at Q4_K_M with an 8K context window. That is the 98.0 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 M2.1 REAP 30 on an 8 GB GPU?

Yes, with the smaller files: the 0.3 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniMax M2.1 REAP 30 GGUF?

It depends on the quant: file is 0.3 GB, IQ1_S is 33.1 GB, IQ1_M is 36.7 GB, IQ2_XXS is 42.7 GB, IQ2_XS is 47.5 GB, IQ2_S is 48.3 GB and 18 more.

What context length does MiniMax M2.1 REAP 30 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 M2.1 REAP 30 GGUF?

The files are on Hugging Face in the mradermacher/MiniMax-M2.1-REAP-30-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 M2.1 REAP 30 use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

Use the IQ1_S quant, which requires about 35.7 GB of VRAM at 8 k context.

Does the model support image inputs?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of MiniMax-M2.1-162B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Minimax models

All Minimax →

Other large models

All large models →