MiniMax M2 needs about 95.9 GB of memory at IQ3_XS (a 93.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 74.8 GB (IQ2_M) to 243.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.
MiniMax M2 is a 229B-parameter Minimax model in GGUF format, quantized by ilintar. Its trained context length is 192K tokens. The repository has 4 quant files, from 74.8 GB (IQ2_M) to 243.1 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 74.8 GB | 77.4 GB | Too big | Get file → | |
| IQ3_XS | 93.3 GB | 95.9 GB | Too big | Get file → | |
| IQ4_NL | 129.0 GB | 131.6 GB | Too big | Get file → | |
| Q8_0 | 243.1 GB | 245.7 GB | Too big | Get file → |
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?
IQ3_XS (93.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ2_M at 74.8 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about MiniMax M2
How much VRAM does MiniMax M2 need?
About 95.9 GB at IQ3_XS with an 8K context window. That is the 93.3 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 77.4 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: IQ2_M is 74.8 GB, IQ3_XS is 93.3 GB, IQ4_NL is 129.0 GB, Q8_0 is 243.1 GB.
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 ilintar/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.