cscec 8bit model needs about 12.4 GB of memory at TQ1_0 (a 9.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
cscec 8bit model is a 32.8B-parameter Cscec model in GGUF format, quantized by jacytong. Its trained context length is 128K tokens. The repository has 1 quant file, from 9.7 GB (TQ1_0) to 9.7 GB (TQ1_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 9.7 GB | 12.4 GB | Too big | Get file → |
What GPU do you need for cscec 8bit model?
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: the best quant that fits is TQ1_0 (9.7 GB file, about 12.4 GB in use).
Which cscec 8bit model quant should you choose?
TQ1_0 (9.7 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about cscec 8bit model
How much VRAM does cscec 8bit model need?
About 12.4 GB at TQ1_0 with an 8K context window. That is the 9.7 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 cscec 8bit model on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of cscec 8bit model GGUF?
It depends on the quant: TQ1_0 is 9.7 GB.
What context length does cscec 8bit model support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 cscec 8bit model GGUF?
The files are on Hugging Face in the jacytong/cscec_8bit_model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.