stt-1b-en_fr needs about 1.1 GB of memory at Q4_0 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU.
stt-1b-en_fr is a 989M-parameter Stt model in GGUF format, quantized by idle-intelligence. The repository has 1 quant file, from 0.6 GB (Q4_0) to 0.6 GB (Q4_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.6 GB | 1.1 GB | Fits | Get file → |
What GPU do you need for stt-1b-en_fr?
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_0 (0.6 GB file, about 1.1 GB in use).
Which stt-1b-en_fr quant should you choose?
Q4_0 (0.6 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 stt-1b-en_fr
How much VRAM does stt-1b-en_fr need?
About 1.1 GB at Q4_0 with an 8K context window. That is the 0.6 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 stt-1b-en_fr on an 8 GB GPU?
Yes, with Q4_0: the 0.6 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of stt-1b-en_fr GGUF?
It depends on the quant: Q4_0 is 0.6 GB.
Where can I download stt-1b-en_fr GGUF?
The files are on Hugging Face in the idle-intelligence/stt-1b-en_fr-q4_0-webgpu repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does stt-1b-en_fr use?
Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.