MiniMax M2.5 needs about 140.9 GB of memory at Q4_K_M (a 138.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 98.7 GB (Q3_K_S) to 187.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.
MiniMax M2.5 is a 229B-parameter Minimax model in GGUF format, quantized by freddm. Its trained context length is 192K tokens. The repository has 3 quant files, from 98.7 GB (Q3_K_S) to 187.8 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 98.7 GB | 101.3 GB | Too big | Get file → | |
| Q4_K_M | 138.3 GB | 140.9 GB | Too big | Get file → | |
| Q6_K | 187.8 GB | 190.3 GB | Too big | Get file → |
What GPU do you need for MiniMax M2.5?
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 M2.5 quant should you choose?
Q4_K_M is the usual starting point for MiniMax M2.5: it balances file size and quality well. Here it is a 138.3 GB file.
If memory is tight, the smallest file is Q3_K_S at 98.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiniMax M2.5
How much VRAM does MiniMax M2.5 need?
About 140.9 GB at Q4_K_M with an 8K context window. That is the 138.3 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 M2.5 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 101.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MiniMax M2.5 GGUF?
It depends on the quant: Q3_K_S is 98.7 GB, Q4_K_M is 138.3 GB, Q6_K is 187.8 GB.
What context length does MiniMax M2.5 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 M2.5 GGUF?
The files are on Hugging Face in the freddm/MiniMax-M2.5-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 M2.5 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.