Canary 1B v2 needs about 1.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.7 GB (Q4_K_M) to 3.9 GB (F32).
1‑Billion‑parameter multilingual speech transcription and translation model
Canary 1B v2 is a 1‑billion parameter model for high‑quality speech transcription and translation across 25 European languages. It supports automatic speech recognition and translation between English and 24 other languages. The model is released under a CC‑BY‑4.0 license.
Good at
- Multilingual ASR for 25 languages
- Speech translation between English and 24 languages
- Automatic punctuation and capitalization
Limits
- No streaming support
- Requires 16 kHz mono WAV input
- No vision capabilities
Best for
- Transcribing multilingual podcasts
- Translating recorded lectures
- Generating timestamped subtitles
Who it’s for. Developers building offline speech‑to‑text or translation tools for European languages. The model is suitable for commercial or non‑commercial use under CC‑BY‑4.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q6_K | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 1.1 GB | 1.8 GB | Fits | Get file → | |
| F16 | 2.0 GB | 2.7 GB | Fits | Get file → | |
| F32 | 3.9 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.74 GB, ~1.3 GB VRAM). For 12 GB VRAM, Q5_K_M (0.84 GB, ~1.4 GB VRAM) or Q6_K (0.93 GB, ~1.5 GB VRAM). Higher precision quants increase VRAM usage accordingly.
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 F16 (2.0 GB file, about 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (3.9 GB file, about 4.9 GB in use).
Which Canary 1B v2 quant should you choose?
Q4_K_M is the usual starting point for Canary 1B v2: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.1 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
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 Q4_K_M 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 F32: the 3.9 GB file needs about 4.9 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: Q4_K_M is 0.7 GB, Q5_K_M is 0.8 GB, Q6_K is 0.9 GB, Q8_0 is 1.1 GB, F16 is 2.0 GB, F32 is 3.9 GB.
Where can I download Canary 1B v2 GGUF?
The files are on Hugging Face in the handy-computer/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, the Q4_K_M quant uses about 1.3 GB VRAM at 8 k context, fitting within an 8 GB GPU.
Does the model support streaming inference?
No, the current GGUF build is not a streaming model and does not expose timestamps in the v1 port.
What languages are supported for translation?
English to 24 languages and 24 languages to English, covering 25 European languages listed in the model card.