Cdbs Half needs about 160.8 GB of memory at F16 (a 159.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Cdbs Half is a 79.7B-parameter Cdbs model in GGUF format, quantized by vili22. Its trained context length is 256K tokens. The repository has 1 quant file, from 159.5 GB (F16) to 159.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 159.5 GB | 160.8 GB | Too big | Get file → |
What GPU do you need for Cdbs Half?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Cdbs Half quant should you choose?
F16 (159.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Cdbs Half
How much VRAM does Cdbs Half need?
About 160.8 GB at F16 with an 8K context window. That is the 159.5 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 Cdbs Half on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 160.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Cdbs Half GGUF?
It depends on the quant: F16 is 159.5 GB.
What context length does Cdbs Half support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Cdbs Half GGUF?
The files are on Hugging Face in the vili22/cdbs repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.