whisper large v2 needs about 1.5 GB of memory at Q4_K (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.9 GB (Q4_K) to 1.0 GB (Q4_1).
whisper large v2 is a 1.54B-parameter Whisper model in GGUF format, quantized by xkeyC. The repository has 2 quant files, from 0.9 GB (Q4_K) to 1.0 GB (Q4_1).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q4_1 | 1.0 GB | 1.6 GB | Fits | Get file → |
What GPU do you need for whisper large 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 Q4_1 (1.0 GB file, about 1.6 GB in use).
Which whisper large v2 quant should you choose?
Q4_K (0.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about whisper large v2
How much VRAM does whisper large v2 need?
About 1.5 GB at Q4_K with an 8K context window. That is the 0.9 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 v2 on an 8 GB GPU?
Yes, with Q4_1: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of whisper large v2 GGUF?
It depends on the quant: Q4_K is 0.9 GB, Q4_1 is 1.0 GB.
Where can I download whisper large v2 GGUF?
The files are on Hugging Face in the xkeyC/whisper-large-v2-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does whisper large v2 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.