whisper large v3 candle needs about 2.4 GB of memory at its main file (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.9 GB to 3.1 GB (F16).
whisper large v3 candle is a 1.54B-parameter Whisper model in GGUF format, quantized by rajansurani. The repository has 3 quant files, from 0.9 GB to 3.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.9 GB | 1.5 GB | Fits | Get file → | |
| — | 1.7 GB | 2.4 GB | Fits | Get file → | |
| F16 | 3.1 GB | 4.0 GB | Fits | Get file → |
What GPU do you need for whisper large v3 candle?
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 F16 (3.1 GB file, about 4.0 GB in use).
Which whisper large v3 candle quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.9 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about whisper large v3 candle
How much VRAM does whisper large v3 candle need?
About 2.4 GB at its main file with an 8K context window. That is the 1.7 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 whisper large v3 candle on an 8 GB GPU?
Yes, with F16: the 3.1 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of whisper large v3 candle GGUF?
It depends on the quant: file is 0.9 GB, file is 1.7 GB, F16 is 3.1 GB.
Where can I download whisper large v3 candle GGUF?
The files are on Hugging Face in the rajansurani/whisper-large-v3-candle repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.