MI

MiniMax M3.1 Flash Maya

MinimaxGGUF by peasantsmithUpdated 2026-10-27
Download on Hugging Face
Parameters426B
Context1024K
Layers60
Architectureminimax-m3
Smallest quant93.0 GB
Quick answer

MiniMax M3.1 Flash Maya needs about 94.5 GB of memory at IQ1_S (a 93.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 93.0 GB (IQ1_S) to 122.4 GB (IQ2_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.

MiniMax M3.1 Flash Maya – a multimodal mixture‑of‑experts LLM

MiniMax M3.1 Flash Maya is a native multimodal mixture‑of‑experts model with 426B parameters and 23B active per token. It supports text, image, and video inputs and offers a 1,000,000 token context window. The model is optimized for inference efficiency with sparse attention and DSpark speculative decoding.

Good at

  • Agentic tasks
  • Coding
  • Cybersecurity

Limits

  • No vision support beyond image/video
  • Large VRAM required for full model
  • License is other

Best for

  • Agentic workflow automation
  • Complex coding assistance
  • Cybersecurity analysis

Who it’s for. Developers and researchers needing a large multimodal LLM with strong agentic and coding capabilities. The model is suitable for projects that can allocate sufficient GPU memory and manage a mixture‑of‑experts architecture.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S93.0 GB (2 parts) 94.5 GB
Too big Get file →
IQ2_XXS122.4 GB (3 parts) 124.0 GB
Too big Get file →

For a 8 GB VRAM setup, the IQ1_S quant (92.98 GB file, ~94.5 GB memory at 8 k context) is too large. The IQ2_XXS quant (122.45 GB file, ~124 GB memory at 8 k context) is also beyond typical consumer GPUs. Use Project Maya to keep the most‑used experts on GPU and compute the rest from RAM, which keeps runtime memory below the full size. The estimates are approximate.

What GPU do you need for MiniMax M3.1 Flash Maya?

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 M3.1 Flash Maya quant should you choose?

IQ1_S (93.0 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureminimax-m3
Parameters426B (approximate, mixture of experts)
Layers60
Trained context1,048,576 tokens
KV cache (fp16)120 KB per token

Source

Quantized bypeasantsmith
FamilyMinimax
Licenseother
Downloads (HF)14,485
Last updated2026-10-27

Frequently asked questions about MiniMax M3.1 Flash Maya

How much VRAM does MiniMax M3.1 Flash Maya need?

About 94.5 GB at IQ1_S with an 8K context window. That is the 93.0 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 M3.1 Flash Maya on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 94.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MiniMax M3.1 Flash Maya GGUF?

It depends on the quant: IQ1_S is 93.0 GB, IQ2_XXS is 122.4 GB.

What context length does MiniMax M3.1 Flash Maya support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.0 GB at 32K.

Where can I download MiniMax M3.1 Flash Maya GGUF?

The files are on Hugging Face in the peasantsmith/MiniMax-M3.1-Flash-Maya-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 M3.1 Flash Maya 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 M3.1 Flash Maya on 8 GB VRAM?

The full model and its quants exceed 8 GB VRAM. Project Maya can reduce GPU usage by keeping only active experts on the GPU, but the overall memory footprint remains large.

Does the model support image and video inputs?

Yes, it accepts text, image, and video inputs and produces text output.

What context length does the model support?

The model supports a context window of up to 1,000,000 tokens.

Other GGUFs of MiniMax-M3.1-Flash

Similar models

Browse all →

More from peasantsmith

All by peasantsmith →

More Minimax models

All Minimax →

Other large models

All large models →