Canary 180M Flash needs about 0.7 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.1 GB (Q4_K_M) to 0.8 GB (F32).
Multilingual speech-to-text and translation model
Canary 180M Flash is a 180‑million‑parameter encoder‑decoder model for multilingual ASR and translation. It supports English, German, French, and Spanish with word‑level timestamps. The model is released under CC‑BY‑4.0 and can be used commercially.
Good at
- ASR in 4 languages
- Bidirectional translation
- Word‑level timestamps
Limits
- No vision support
- Not streaming
- Requires 8‑k context for memory estimates
Best for
- Transcribing podcasts
- Translating short audio clips
- Generating subtitles
Who it’s for. Developers building offline speech‑to‑text or translation tools. The model runs on CPU or GPU via llama.cpp or transcribe.cpp and is suitable for embedded or edge deployments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q8_0 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.4 GB | 0.9 GB | Fits | Get file → | |
| F32 | 0.8 GB | 1.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.14 GB) or Q5_K_M (0.16 GB). If 4 GB VRAM, Q4_K_M is recommended. For higher precision, Q8_0 (0.22 GB) or F16 (0.38 GB) can be used on systems with 8 GB or more.
What GPU do you need for Canary 180M Flash?
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 F32 (0.8 GB file, about 1.3 GB in use).
Which Canary 180M Flash quant should you choose?
Q4_K_M is the usual starting point for Canary 180M Flash: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.2 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 180M Flash
How much VRAM does Canary 180M Flash need?
About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.1 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 180M Flash on an 8 GB GPU?
Yes, with F32: the 0.8 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Canary 180M Flash GGUF?
It depends on the quant: Q4_K_M is 0.1 GB, Q5_K_M is 0.2 GB, Q6_K is 0.2 GB, Q8_0 is 0.2 GB, F16 is 0.4 GB, F32 is 0.8 GB.
Where can I download Canary 180M Flash GGUF?
The files are on Hugging Face in the handy-computer/canary-180m-flash-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 180M Flash 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 180M Flash on 4 GB VRAM?
Yes, the Q4_K_M quantized file is 0.14 GB and requires about 0.7 GB VRAM at 8k context.
Does this model support image input?
No, it only accepts 16 kHz mono WAV audio files.
Is the model free for commercial use?
Yes, it is licensed under CC‑BY‑4.0, which allows commercial use.