masa v1 needs about 0.5 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.0 GB (Q4_K_M) to 17.7 GB (Q8_0).
masa v1 is a 18.8B-parameter Masa model in GGUF format, quantized by MASAYUKI-EMO. The repository has 6 quant files, from 5.9 GB (Q5_K_XL) to 17.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_XL | 5.9 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_M | 7.0 GB | 8.4 GB | Too big | Get file → | |
| Q4_K_M | 11.5 GB | 13.3 GB | Too big | Get file → | |
| Q4_K_M | 13.5 GB | 15.6 GB | Too big | Get file → | |
| Q8_0 | 17.7 GB | 20.3 GB | Too big | Get file → |
What GPU do you need for masa v1?
These figures add the file size, an fp16 KV cache at an 8K context window 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 Q4_K_M (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (0.0 GB file, about 0.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_XL (5.9 GB file, about 7.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (7.0 GB file, about 8.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (13.5 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (17.7 GB file, about 20.3 GB in use).
Which masa v1 quant should you choose?
Q4_K_M is the usual starting point for masa v1: it balances file size and quality well. Here it is a 0.0 GB file.
The Q8_0 file is 17.7 GB, about Infinity 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about masa v1
How much VRAM does masa v1 need?
About 0.5 GB at Q4_K_M with an 8K context window. That is the 0.0 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 masa v1 on an 8 GB GPU?
Yes, with Q5_K_XL: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of masa v1 GGUF?
It depends on the quant: Q4_K_M is 0.0 GB, Q5_K_XL is 5.9 GB, Q5_K_M is 7.0 GB, Q4_K_M is 11.5 GB, Q4_K_M is 13.5 GB, Q8_0 is 17.7 GB.
Where can I download masa v1 GGUF?
The files are on Hugging Face in the MASAYUKI-EMO/masa_v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.