Canary 1B 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 4.1 GB (F32).
1 Billion‑parameter multilingual speech‑to‑text and translation model
Canary 1B is a 1 B parameter encoder‑decoder model with a 24‑layer FastConformer encoder and a 24‑layer Transformer decoder. It supports automatic speech‑to‑text in English, German, French, and Spanish, and translation between these languages. The model is available in GGUF format for use with transcribe.cpp.
Good at
- Multilingual ASR
- Speech‑to‑text translation
- Offline inference
Limits
- Requires 8 k context for full operation
- Non‑commercial CC‑BY‑NC‑4.0 license
- No vision support
Best for
- Transcribing podcasts in multiple languages
- Batch translation of audio files
- Developing offline speech tools
Who it’s for. Developers building offline multilingual speech‑to‑text or translation applications who need a compact, non‑commercial model. The model is suitable for research and hobby projects that require multilingual support without streaming capability.
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 | 1.2 GB | 1.8 GB | Fits | Get file → | |
| F16 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| F32 | 4.1 GB | 5.1 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (0.73 GB) or Q5_K_M (0.84 GB) are suitable, providing about 1.3–1.4 GB VRAM usage at 8 k context. If more VRAM is available, Q6_K (0.93 GB) or Q8_0 (1.16 GB) give higher precision. F16 and F32 are too large for typical consumer GPUs.
What GPU do you need for Canary 1B?
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 2.8 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (4.1 GB file, about 5.1 GB in use).
Which Canary 1B quant should you choose?
Q4_K_M is the usual starting point for Canary 1B: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.2 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
How much VRAM does Canary 1B 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 on an 8 GB GPU?
Yes, with F32: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Canary 1B 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 1.2 GB, F16 is 2.0 GB, F32 is 4.1 GB.
Where can I download Canary 1B GGUF?
The files are on Hugging Face in the handy-computer/canary-1b-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 use?
Hugging Face lists the license as cc-by-nc-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 on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quantizations will fit within 8 GB VRAM, with estimated usage around 1.3–1.4 GB at 8 k context.
Does Canary 1B support streaming inference?
No, Canary 1B is not a streaming model; it processes entire audio files offline.
What license applies to the GGUF version?
The GGUF files are licensed under CC‑BY‑NC‑4.0, allowing non‑commercial use only.