canary 1b v2 needs about 1.3 GB of memory at Q5_0 (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 2.0 GB.
Multilingual ASR and speech translation model with 25 European languages
Canary 1B v2 is a 0.98‑billion parameter model designed for automatic speech recognition and speech translation. It supports 25 European languages and provides explicit source and target language tokens for clear task definition.
Good at
- Speech transcription in 25 languages
- Speech translation X→English and English→X
- Automatic punctuation and capitalization
Limits
- No vision support
- Requires explicit language tokens
- License CC‑BY‑4.0
Best for
- Transcribing multilingual meetings
- Translating spoken content in real‑time
- Generating timestamped subtitles
Who it’s for. Developers building multilingual voice assistants or transcription services. The model is suitable for commercial or non‑commercial use under a CC‑BY‑4.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q5_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 1.0 GB | 1.7 GB | Fits | Get file → | |
| — | 2.0 GB | 2.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (file size 0.61 GB, estimated 1.2 GB memory at 8 k context). For 12 GB VRAM, Q5_0 (0.72 GB, 1.3 GB memory). For 16 GB VRAM, Q8_0 (1.05 GB, 1.7 GB memory). The unknown quant files are larger and need more memory.
What GPU do you need for canary 1b 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 (2.0 GB file, about 2.7 GB in use).
Which canary 1b v2 quant should you choose?
Q5_0 (0.7 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.
If memory is tight, the smallest file is the first one in the table at 0.0 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 canary 1b v2
How much VRAM does canary 1b v2 need?
About 1.3 GB at Q5_0 with an 8K context window. That is the 0.7 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 canary 1b v2 on an 8 GB GPU?
Yes, with the smaller files: the 2.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of canary 1b v2 GGUF?
It depends on the quant: file is 0.0 GB, Q4_K is 0.6 GB, Q5_0 is 0.7 GB, Q8_0 is 1.0 GB, file is 2.0 GB.
Where can I download canary 1b v2 GGUF?
The files are on Hugging Face in the cstr/canary-1b-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 canary 1b v2 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.
Can I run Canary 1B v2 on 8 GB VRAM?
Yes, using the Q4_K quantized file which requires about 1.2 GB of VRAM at 8 k context.
Does the model support automatic language detection?
No, it requires explicit source and target language tokens to avoid ambiguity.
What license applies to this model?
The model is released under a CC‑BY‑4.0 license, allowing commercial and non‑commercial use.