saricles MiniMax M2.7 REAP 172B A10B ROCMFPX needs about 128.9 GB of memory at Q3_0 (a 126.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 97.3 GB (Q4_0) to 159.9 GB (Q6_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.3 GB.
saricles MiniMax M2.7 REAP 172B A10B ROCMFPX is a 173B-parameter Saricles model in GGUF format, quantized by rcmorano. Its trained context length is 192K tokens. The repository has 3 quant files, from 97.3 GB (Q4_0) to 159.9 GB (Q6_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 97.3 GB | 99.9 GB | Too big | Get file → | |
| Q3_0 | 126.3 GB | 128.9 GB | Too big | Get file → | |
| Q6_0 | 159.9 GB | 162.5 GB | Too big | Get file → |
What GPU do you need for saricles MiniMax M2.7 REAP 172B A10B ROCMFPX?
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 saricles MiniMax M2.7 REAP 172B A10B ROCMFPX quant should you choose?
Q3_0 (126.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q4_0 at 97.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about saricles MiniMax M2.7 REAP 172B A10B ROCMFPX
How much VRAM does saricles MiniMax M2.7 REAP 172B A10B ROCMFPX need?
About 128.9 GB at Q3_0 with an 8K context window. That is the 126.3 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 saricles MiniMax M2.7 REAP 172B A10B ROCMFPX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 99.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of saricles MiniMax M2.7 REAP 172B A10B ROCMFPX GGUF?
It depends on the quant: Q4_0 is 97.3 GB, Q3_0 is 126.3 GB, Q6_0 is 159.9 GB.
What context length does saricles MiniMax M2.7 REAP 172B A10B ROCMFPX 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 saricles MiniMax M2.7 REAP 172B A10B ROCMFPX GGUF?
The files are on Hugging Face in the rcmorano/saricles-MiniMax-M2.7-REAP-172B-A10B-ROCMFPX repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does saricles MiniMax M2.7 REAP 172B A10B ROCMFPX 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.