FastHunyuan gguf Q3 K M needs about 7.5 GB of memory at Q3_K_M (a 6.2 GB file) with an 8K context window, so it fits on a 8 GB GPU.
FastHunyuan gguf Q3 K M is a 12.8B-parameter Fasthunyuan model in GGUF format, quantized by roleplaiapp. The repository has 1 quant file, from 6.2 GB (Q3_K_M) to 6.2 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 6.2 GB | 7.5 GB | Tight | Get file → |
What GPU do you need for FastHunyuan gguf Q3 K M?
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: the best quant that fits is Q3_K_M (6.2 GB file, about 7.5 GB in use).
Which FastHunyuan gguf Q3 K M quant should you choose?
Q3_K_M (6.2 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about FastHunyuan gguf Q3 K M
How much VRAM does FastHunyuan gguf Q3 K M need?
About 7.5 GB at Q3_K_M with an 8K context window. That is the 6.2 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 FastHunyuan gguf Q3 K M on an 8 GB GPU?
Yes, with Q3_K_M: the 6.2 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FastHunyuan gguf Q3 K M GGUF?
It depends on the quant: Q3_K_M is 6.2 GB.
Where can I download FastHunyuan gguf Q3 K M GGUF?
The files are on Hugging Face in the roleplaiapp/FastHunyuan-gguf-Q3_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.