caca Q4 K M needs about 2.3 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU.
caca Q4 K M is a 2.51B-parameter Caca model in GGUF format, quantized by Gargaz. Its trained context length is 8K tokens. The repository has 1 quant file, from 1.6 GB (Q4_K_M) to 1.6 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.6 GB | 2.3 GB | Fits | Get file → |
What GPU do you need for caca Q4 K M?
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: the best quant that fits is Q4_K_M (1.6 GB file, about 2.3 GB in use).
Which caca Q4 K M quant should you choose?
Q4_K_M is the usual starting point for caca Q4 K M: it balances file size and quality well. Here it is a 1.6 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about caca Q4 K M
How much VRAM does caca Q4 K M need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.6 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 caca Q4 K M on an 8 GB GPU?
Yes, with Q4_K_M: the 1.6 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of caca Q4 K M GGUF?
It depends on the quant: Q4_K_M is 1.6 GB.
What context length does caca Q4 K M support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.
Where can I download caca Q4 K M GGUF?
The files are on Hugging Face in the Gargaz/caca-Q4_K_M-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.