MiniMax M3 needs about 265.8 GB of memory at Q4_K_M (a 264.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 0.5 GB to 317.0 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.
MiniMax M3 – a 426B‑parameter multimodal model with 1M token context
MiniMax M3 is a native multimodal model with 426B parameters and a 1M token context. It supports reasoning, tools, and vision. The model uses MiniMax Sparse Attention for efficient long‑context processing.
Good at
- Long‑context reasoning
- Multimodal inference
- Agentic coding tasks
Limits
- Requires large VRAM for full precision
- No vision support in some frameworks
- License type is other
Best for
- Chatbots needing 1M context
- Multimodal research prototypes
- Agentic coding assistants
Who it’s for. Developers and researchers who need a large multimodal model with extended context. The model is suitable for applications that can accommodate its memory demands and benefit from sparse attention optimization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 2.0 GB | Fits | Get file → | |
| IQ2_S | 143.9 GB (4 parts) | 145.4 GB | Too big | Get file → | |
| IQ3_S | 159.0 GB (5 parts) | 160.5 GB | Too big | Get file → | |
| IQ4_XS | 203.1 GB (6 parts) | 204.6 GB | Too big | Get file → | |
| Q4_K_M | 264.3 GB (7 parts) | 265.8 GB | Too big | Get file → | |
| Q5_K_M | 317.0 GB (8 parts) | 318.5 GB | Too big | Get file → |
For 8 GB VRAM use the IQ2_S quant (143.9 GB file, ~145.4 GB memory at 8k context). For 16 GB VRAM use IQ3_S (158.96 GB file, ~160.5 GB memory). For 32 GB VRAM use Q4_K_M (264.26 GB file, ~265.8 GB memory). Estimates are approximate.
What GPU do you need for MiniMax M3?
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 2.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
Which MiniMax M3 quant should you choose?
Q4_K_M is the usual starting point for MiniMax M3: it balances file size and quality well. Here it is a 264.3 GB file.
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
Source
Frequently asked questions about MiniMax M3
How much VRAM does MiniMax M3 need?
About 265.8 GB at Q4_K_M with an 8K context window. That is the 264.3 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 M3 on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniMax M3 GGUF?
It depends on the quant: file is 0.5 GB, IQ2_S is 143.9 GB, IQ3_S is 159.0 GB, IQ4_XS is 203.1 GB, Q4_K_M is 264.3 GB, Q5_K_M is 317.0 GB.
What context length does MiniMax M3 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 GGUF?
The files are on Hugging Face in the AesSedai/MiniMax-M3-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 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 on 8 GB VRAM?
Only with the IQ2_S quant, which requires about 145.4 GB memory at 8k context – not feasible on 8 GB VRAM.
Does MiniMax M3 support vision?
Yes, it has detected vision ability, but some inference frameworks may not expose it.