MiniMax M2.1 REAP 50 needs about 73.0 GB of memory at Q4_K_M (a 70.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 42.5 GB (Q2_K) to 123.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.
MiniMax M2.1 REAP 50 – 116B parameter LLM for coding, reasoning, and tool use
MiniMax M2.1 REAP 50 is a 116‑billion‑parameter model built on the minimax‑m2 architecture. It supports coding, reasoning, and tool‑based tasks. The model is released under the Apache‑2.0 license and is available in multiple GGUF quantizations.
Good at
- Coding tasks
- Logical reasoning
- Tool integration
Limits
- No vision support
- Large context requires high VRAM
- Requires 8‑k context for estimates
Best for
- Developers needing code generation
- Researchers exploring reasoning models
- Tool‑enabled automation scripts
Who it’s for. Engineers and researchers who need a large language model capable of coding and reasoning. The model is suitable for environments that can handle its memory requirements and support GGUF usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 42.5 GB | 45.1 GB | Too big | Get file → | |
| Q3_K_S | 50.3 GB | 52.9 GB | Too big | Get file → | |
| Q3_K_M | 55.7 GB | 58.3 GB | Too big | Get file → | |
| Q3_K_L | 60.3 GB | 62.9 GB | Too big | Get file → | |
| IQ4_XS | 62.8 GB | 65.3 GB | Too big | Get file → | |
| Q4_K_S | 66.2 GB | 68.8 GB | Too big | Get file → | |
| Q4_K_M | 70.4 GB | 73.0 GB | Too big | Get file → | |
| Q5_K_S | 80.1 GB | 82.7 GB | Too big | Get file → | |
| Q5_K_M | 82.6 GB | 85.1 GB | Too big | Get file → | |
| Q6_K | 95.5 GB | 98.1 GB | Too big | Get file → | |
| Q8_0 | 123.7 GB | 126.3 GB | Too big | Get file → |
For 8‑GB VRAM, use Q2_K (file size 42.54 GB, estimated memory 45.1 GB). For 16‑GB VRAM, Q4_K_M (70.38 GB, 73 GB). For 32‑GB VRAM, Q5_K_M (82.57 GB, 85.1 GB). These estimates are approximate.
What GPU do you need for MiniMax M2.1 REAP 50?
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: the best quant that fits is Q2_K (42.5 GB file, about 45.1 GB in use).
Which MiniMax M2.1 REAP 50 quant should you choose?
Q4_K_M is the usual starting point for MiniMax M2.1 REAP 50: it balances file size and quality well. Here it is a 70.4 GB file.
The Q8_0 file is 123.7 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 42.5 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 M2.1 REAP 50
How much VRAM does MiniMax M2.1 REAP 50 need?
About 73.0 GB at Q4_K_M with an 8K context window. That is the 70.4 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 REAP 50 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 45.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MiniMax M2.1 REAP 50 GGUF?
It depends on the quant: Q2_K is 42.5 GB, Q3_K_S is 50.3 GB, Q3_K_M is 55.7 GB, Q3_K_L is 60.3 GB, IQ4_XS is 62.8 GB, Q4_K_S is 66.2 GB and 5 more.
What context length does MiniMax M2.1 REAP 50 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 REAP 50 GGUF?
The files are on Hugging Face in the mradermacher/MiniMax-M2.1-REAP-50-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 REAP 50 use?
Hugging Face lists the license as apache-2.0. 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 REAP 50 on 8 GB VRAM?
The Q2_K quant requires about 45.1 GB of VRAM at 8‑k context, so 8 GB is insufficient.
Does this model support vision tasks?
No, the model does not support vision.