candle quantized Puffin Phi v2 needs about 1.4 GB of memory at its main file (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU.
candle quantized Puffin Phi v2 is a 1.41B-parameter Candle model in GGUF format, quantized by diablo98. The repository has 1 quant file, from 0.8 GB to 0.8 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.8 GB | 1.4 GB | Fits | Get file → |
What GPU do you need for candle quantized Puffin Phi v2?
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: the best quant that fits is the main file (0.8 GB file, about 1.4 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about candle quantized Puffin Phi v2
How much VRAM does candle quantized Puffin Phi v2 need?
About 1.4 GB at its main file with an 8K context window. That is the 0.8 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 candle quantized Puffin Phi v2 on an 8 GB GPU?
Yes, with the smaller files: the 0.8 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of candle quantized Puffin Phi v2 GGUF?
It depends on the quant: file is 0.8 GB.
Where can I download candle quantized Puffin Phi v2 GGUF?
The files are on Hugging Face in the diablo98/candle-quantized-Puffin-Phi-v2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.