MiniMax M2.1 needs about 141.2 GB of memory at Q4_K_M (a 138.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 0.5 GB to 243.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.
MiniMax M2.1 – 230B parameter model for coding and instruction following
MiniMax M2.1 is a 230 billion‑parameter model optimized for coding, tool use, and long‑horizon planning. It supports up to 196 608 context tokens and is available in multiple GGUF quantizations. The model is open‑source and can be run locally with llama.cpp.
Good at
- Robust coding and tool use
- Long‑horizon instruction following
- Multilingual software development
Limits
- Requires large VRAM for high‑quality quants
- No vision support
- License is other (not MIT)
Best for
- Local code generation with limited GPU memory
- Building autonomous coding agents
- Fine‑tuning for specialized software tasks
Who it’s for. Developers and researchers who need a powerful, open‑source model for coding and instruction tasks. The model is suitable for local deployment on systems with sufficient VRAM and for integration into autonomous application pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 3.1 GB | Fits | Get file → | |
| IQ1_S | 47.0 GB | 49.6 GB | Too big | Get file → | |
| IQ1_M | 49.0 GB | 51.6 GB | Too big | Get file → | |
| IQ2_XXS | 54.7 GB (2 parts) | 57.3 GB | Too big | Get file → | |
| IQ2_XS | 63.1 GB (2 parts) | 65.7 GB | Too big | Get file → | |
| IQ2_S | 63.4 GB (2 parts) | 65.9 GB | Too big | Get file → | |
| IQ2_M | 72.0 GB (2 parts) | 74.6 GB | Too big | Get file → | |
| Q2_K | 79.8 GB (2 parts) | 82.4 GB | Too big | Get file → | |
| Q2_K_L | 80.4 GB (3 parts) | 83.0 GB | Too big | Get file → | |
| IQ3_XXS | 90.1 GB (3 parts) | 92.7 GB | Too big | Get file → | |
| IQ3_XS | 93.8 GB (3 parts) | 96.3 GB | Too big | Get file → | |
| Q3_K_S | 99.1 GB (3 parts) | 101.7 GB | Too big | Get file → | |
| IQ3_M | 104.0 GB (3 parts) | 106.5 GB | Too big | Get file → | |
| Q3_K_M | 104.0 GB (3 parts) | 106.5 GB | Too big | Get file → | |
| Q3_K_L | 108.2 GB (3 parts) | 110.8 GB | Too big | Get file → | |
| Q3_K_XL | 108.7 GB (3 parts) | 111.3 GB | Too big | Get file → | |
| IQ4_XS | 122.2 GB (4 parts) | 124.7 GB | Too big | Get file → | |
| IQ4_NL | 129.2 GB (4 parts) | 131.8 GB | Too big | Get file → | |
| Q4_0 | 131.3 GB (4 parts) | 133.9 GB | Too big | Get file → | |
| Q4_K_S | 133.8 GB (4 parts) | 136.3 GB | Too big | Get file → | |
| Q4_K_M | 138.6 GB (4 parts) | 141.2 GB | Too big | Get file → | |
| Q4_K_L | 139.0 GB (4 parts) | 141.6 GB | Too big | Get file → | |
| Q4_1 | 143.3 GB (4 parts) | 145.9 GB | Too big | Get file → | |
| Q5_K_S | 157.6 GB (4 parts) | 160.1 GB | Too big | Get file → | |
| Q5_K_M | 162.4 GB (5 parts) | 165.0 GB | Too big | Get file → | |
| Q6_K | 187.8 GB (5 parts) | 190.4 GB | Too big | Get file → | |
| Q8_0 | 243.1 GB (7 parts) | 245.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 47.01 GB, ~49.6 GB memory at 8 k context). For 16 GB VRAM, IQ2_S (63.35 GB, ~65.9 GB memory) or Q2_K (79.82 GB, ~82.4 GB). For 24 GB VRAM, Q3_K_M (103.96 GB, ~106.5 GB memory).
What GPU do you need for MiniMax M2.1?
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 3.1 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 3.1 GB in use).
Which MiniMax M2.1 quant should you choose?
Q4_K_M is the usual starting point for MiniMax M2.1: it balances file size and quality well. Here it is a 138.6 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 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 M2.1
How much VRAM does MiniMax M2.1 need?
About 141.2 GB at Q4_K_M with an 8K context window. That is the 138.6 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 M2.1 on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniMax M2.1 GGUF?
It depends on the quant: file is 0.5 GB, IQ1_S is 47.0 GB, IQ1_M is 49.0 GB, IQ2_XXS is 54.7 GB, IQ2_XS is 63.1 GB, IQ2_S is 63.4 GB and 21 more.
What context length does MiniMax M2.1 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 M2.1 GGUF?
The files are on Hugging Face in the bartowski/MiniMaxAI_MiniMax-M2.1-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 M2.1 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 M2.1 on 8 GB VRAM?
Use the IQ1_S quant, which requires about 49.6 GB of VRAM at 8 k context. It is the smallest quant that supports the full model.
Does MiniMax M2.1 support vision?
No, the model does not include vision capabilities.
What is the maximum context length?
The model was trained with 196 608 context tokens.