model needs about 21.4 GB of memory at Q8_0 (a 18.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 18.7 GB (Q8_0) to 34.7 GB (BF16).
model is a 17.3B-parameter Model model in GGUF format, quantized by vivi168. The repository has 2 quant files, from 18.7 GB (Q8_0) to 34.7 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 18.7 GB | 21.4 GB | Too big | Get file → | |
| BF16 | 34.7 GB | 39.4 GB | Too big | Get file → |
What GPU do you need for model?
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: 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 Q8_0 (18.7 GB file, about 21.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (18.7 GB file, about 21.4 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (34.7 GB file, about 39.4 GB in use).
Which model quant should you choose?
Q8_0 (18.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about model
How much VRAM does model need?
About 21.4 GB at Q8_0 with an 8K context window. That is the 18.7 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 model on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of model GGUF?
It depends on the quant: Q8_0 is 18.7 GB, BF16 is 34.7 GB.
Where can I download model GGUF?
The files are on Hugging Face in the vivi168/model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.