MOSS-Audio-8B-Thinking needs about 9.3 GB of memory at Q6_K (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 7.9 GB (Q6_K) to 7.9 GB (Q6_K).
MOSS-Audio-8B-Thinking is a 9.05B-parameter Moss model in GGUF format, quantized by akakaiy. The repository has 3 quant files, from 7.9 GB (Q6_K) to 7.9 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 7.9 GB | 9.3 GB | Too big | Get file → | |
| Q6_K | 7.9 GB | 9.3 GB | Too big | Get file → | |
| Q6_K | 7.9 GB | 9.3 GB | Too big | Get file → |
What GPU do you need for MOSS-Audio-8B-Thinking?
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: 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: the best quant that fits is Q6_K (7.9 GB file, about 9.3 GB in use).
Which MOSS-Audio-8B-Thinking quant should you choose?
Q6_K (7.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q6_K at 7.9 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MOSS-Audio-8B-Thinking
How much VRAM does MOSS-Audio-8B-Thinking need?
About 9.3 GB at Q6_K with an 8K context window. That is the 7.9 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 MOSS-Audio-8B-Thinking on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MOSS-Audio-8B-Thinking GGUF?
It depends on the quant: Q6_K is 7.9 GB, Q6_K is 7.9 GB, Q6_K is 7.9 GB.
Where can I download MOSS-Audio-8B-Thinking GGUF?
The files are on Hugging Face in the akakaiy/MOSS-Audio-8B-Thinking-ru repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MOSS-Audio-8B-Thinking 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.