cali 3 12b 012126 needs about 26.9 GB of memory at BF16 (a 23.5 GB file) with an 8K context window, so it fits on a 32 GB GPU.
cali 3 12b 012126 is a 11.8B-parameter Cali model in GGUF format, quantized by jayanthanc. Its trained context length is 128K tokens. The repository has 1 quant file, from 23.5 GB (BF16) to 23.5 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 23.5 GB | 26.9 GB | Too big | Get file → |
What GPU do you need for cali 3 12b 012126?
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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is BF16 (23.5 GB file, about 26.9 GB in use).
Which cali 3 12b 012126 quant should you choose?
BF16 (23.5 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
Source
Frequently asked questions about cali 3 12b 012126
How much VRAM does cali 3 12b 012126 need?
About 26.9 GB at BF16 with an 8K context window. That is the 23.5 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 cali 3 12b 012126 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of cali 3 12b 012126 GGUF?
It depends on the quant: BF16 is 23.5 GB.
What context length does cali 3 12b 012126 support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download cali 3 12b 012126 GGUF?
The files are on Hugging Face in the jayanthanc/cali-3-12b-012126-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.