MiniMax M2.7 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 7 quants, from 81.6 GB (Q2_K) to 457.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.
229B parameter MoE model for coding and agentic workflows
MiniMax M2.7 is a 229B parameter Mixture‑of‑Experts model with ~10B active parameters per token. It excels at reasoning, tool use, and complex coding tasks. The model is trained on 196608 context tokens and is available in multiple GGUF quantizations.
Good at
- reasoning
- tool use
- advanced coding
Limits
- no vision support
- requires large memory
- license is other
Best for
- coding and refactoring
- agent workflow orchestration
- debugging and monitoring
Who it’s for. Developers and researchers needing high‑level reasoning and coding assistance. The model is suited for building agent teams and complex productivity pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 81.6 GB | 84.2 GB | Too big | Get file → | |
| Q3_K_M | 109.3 GB | 111.9 GB | Too big | Get file → | |
| Q4_K_M | 138.3 GB | 140.9 GB | Too big | Get file → | |
| Q5_K_M | 162.3 GB | 164.9 GB | Too big | Get file → | |
| Q6_K | 187.8 GB | 190.3 GB | Too big | Get file → | |
| Q8_0 | 243.1 GB | 245.7 GB | Too big | Get file → | |
| BF16 | 457.5 GB | 460.1 GB | Too big | Get file → |
For 8k context, Q4_K_M needs about 140.9GB VRAM, Q3_K_M about 111.9GB, Q2_K about 84.2GB. Choose the smallest quant that meets your memory budget. BF16 requires ~460.1GB and is the largest option.
What GPU do you need for MiniMax M2.7?
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 M2.7 quant should you choose?
Q4_K_M is the usual starting point for MiniMax M2.7: it balances file size and quality well. Here it is a 138.3 GB file.
The Q8_0 file is 243.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 81.6 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 M2.7
How much VRAM does MiniMax M2.7 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 M2.7 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 84.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MiniMax M2.7 GGUF?
It depends on the quant: Q2_K is 81.6 GB, Q3_K_M is 109.3 GB, Q4_K_M is 138.3 GB, Q5_K_M is 162.3 GB, Q6_K is 187.8 GB, Q8_0 is 243.1 GB and 1 more.
What context length does MiniMax M2.7 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 M2.7 GGUF?
The files are on Hugging Face in the dennny123/MiniMax-M2.7-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 M2.7 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 M2.7 on 8 GB VRAM?
No. Even the smallest quant Q2_K requires about 84.2GB VRAM at 8k context.
How many parameters are active per token?
Approximately 10B parameters are active per token, though the model has 229B total.
Does MiniMax M2.7 support vision?
No, the model has no vision capability.