m needs about 22.4 GB of memory at its main file (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 19.8 GB to 19.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
m is a 32.8B-parameter Papiang model in GGUF format, quantized by papiang. Its trained context length is 40K tokens. The repository has 2 quant files, from 19.8 GB to 19.8 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 19.8 GB | 22.4 GB | Too big | Get file → | |
| — | 19.8 GB | 22.4 GB | Too big | Get file → |
What GPU do you need for m?
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: the best quant that fits is the main file (19.8 GB file, about 22.4 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about m
How much VRAM does m need?
About 22.4 GB at its main file with an 8K context window. That is the 19.8 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 m on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of m GGUF?
It depends on the quant: file is 19.8 GB, file is 19.8 GB.
What context length does m support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download m GGUF?
The files are on Hugging Face in the papiang/m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.