testing punica 001 GGUFs needs about 10.5 GB of memory at Q5_K_S (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.3 GB (Q5_K_S) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.
testing punica 001 GGUFs is a 12B-parameter Testing model in GGUF format, quantized by kromquant. Its trained context length is 128K tokens. The repository has 2 quant files, from 8.3 GB (Q5_K_S) to 12.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 8.3 GB | 10.5 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.9 GB | Too big | Get file → |
What GPU do you need for testing punica 001 GGUFs?
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: the best quant that fits is Q5_K_S (8.3 GB file, about 10.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.9 GB in use).
Which testing punica 001 GGUFs quant should you choose?
Q5_K_S (8.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about testing punica 001 GGUFs
How much VRAM does testing punica 001 GGUFs need?
About 10.5 GB at Q5_K_S with an 8K context window. That is the 8.3 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 testing punica 001 GGUFs on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of testing punica 001 GGUFs GGUF?
It depends on the quant: Q5_K_S is 8.3 GB, Q8_0 is 12.7 GB.
What context length does testing punica 001 GGUFs support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.
Where can I download testing punica 001 GGUFs GGUF?
The files are on Hugging Face in the kromquant/testing-punica-001-GGUFs repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.