cerebras/MiniMax-M2.5-REAP-172B-A10B needs about 106.9 GB of memory at Q4_K_M (a 104.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 62.9 GB (Q2_K) to 183.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.
MiniMax-M2.5-REAP-172B-A10B – a 172B‑parameter sparse MoE model
MiniMax-M2.5-REAP-172B-A10B is a memory‑efficient compressed variant of MiniMax-M2.5. It retains near‑lossless performance on code generation, math, reasoning, and tool calling while reducing parameters to 172B and pruning 25% of experts.
Good at
- Reasoning
- Tool calling
- Code generation
Limits
- No vision support
- Large context length requires high VRAM
- License is other
Best for
- Local deployment on limited GPU
- Academic research with constrained resources
- Testing sparse MoE models
Who it’s for. Developers and researchers needing a compact, high‑capacity language model that supports reasoning and tool usage without the need for custom patches. Suitable for environments where GPU memory is a limiting factor.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 62.9 GB | 65.5 GB | Too big | Get file → | |
| Q3_K_S | 74.5 GB | 77.1 GB | Too big | Get file → | |
| Q3_K_M | 82.5 GB | 85.1 GB | Too big | Get file → | |
| Q3_K_L | 89.3 GB | 91.9 GB | Too big | Get file → | |
| IQ4_XS | 93.0 GB | 95.6 GB | Too big | Get file → | |
| Q4_K_S | 98.1 GB | 100.7 GB | Too big | Get file → | |
| Q4_K_M | 104.4 GB | 106.9 GB | Too big | Get file → | |
| Q5_K_S | 118.8 GB | 121.4 GB | Too big | Get file → | |
| Q5_K_M | 122.4 GB | 125.0 GB | Too big | Get file → | |
| Q6_K | 141.6 GB | 144.2 GB | Too big | Get file → | |
| Q8_0 | 183.4 GB | 186.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (62.92 GB file, ~65.5 GB memory). For 16 GB VRAM, Q3_K_S (74.51 GB file, ~77.1 GB memory). For 32 GB VRAM, Q4_K_M (104.36 GB file, ~106.9 GB memory).
What GPU do you need for cerebras/MiniMax-M2.5-REAP-172B-A10B?
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 cerebras/MiniMax-M2.5-REAP-172B-A10B quant should you choose?
Q4_K_M is the usual starting point for cerebras/MiniMax-M2.5-REAP-172B-A10B: it balances file size and quality well. Here it is a 104.4 GB file.
The Q8_0 file is 183.4 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 62.9 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 cerebras/MiniMax-M2.5-REAP-172B-A10B
How much VRAM does cerebras/MiniMax-M2.5-REAP-172B-A10B need?
About 106.9 GB at Q4_K_M with an 8K context window. That is the 104.4 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 cerebras/MiniMax-M2.5-REAP-172B-A10B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 65.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of cerebras/MiniMax-M2.5-REAP-172B-A10B GGUF?
It depends on the quant: Q2_K is 62.9 GB, Q3_K_S is 74.5 GB, Q3_K_M is 82.5 GB, Q3_K_L is 89.3 GB, IQ4_XS is 93.0 GB, Q4_K_S is 98.1 GB and 5 more.
What context length does cerebras/MiniMax-M2.5-REAP-172B-A10B 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 cerebras/MiniMax-M2.5-REAP-172B-A10B GGUF?
The files are on Hugging Face in the mradermacher/MiniMax-M2.5-REAP-172B-A10B-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 cerebras/MiniMax-M2.5-REAP-172B-A10B 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 this model on 8 GB VRAM?
The smallest quant, Q2_K, requires about 65.5 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does this model support vision tasks?
No, the model has no vision capabilities.
Is the model compatible with vLLM?
Yes, it works with vanilla vLLM without source modifications.