Alternatives to canary-1b-flash

canary-1b-flash alternatives

canary-1b-flash's smallest published quantization is 0.63 GiB. The models below do the same job with a different trade — less memory, comparable size, or a more permissive licence.

From the file· sizes from summed file bytes

Meaningfully smaller

under 70% of its smallest quantization
ModelParamsSmallestQuantsLicence
nemotron-3.5-asr-streaming-0.6b638M0.38 GiB8other
parakeet-tdt-0.6b-v3627M0.39 GiB10cc-by-4.0
whisper-medium764M0.25 GiB19apache-2.0
canary-180m-flash189M0.13 GiB6cc-by-4.0
whisper-large-v3-turbo809M0.27 GiB31apache-2.0
parakeet-tdt-0.6b-v2618M0.37 GiB8cc-by-4.0
GigaAM-v3223M0.17 GiB18mit
canary-1b-v2980M0.37 GiB12cc-by-4.0

Comparable in size

within ±40%, so a like-for-like swap
ModelParamsSmallestQuantsLicence
parakeet-unified-en-0.6b618M0.44 GiB6cc-by-4.0
whisper-large-v31.5B0.49 GiB18apache-2.0
Qwen3-ASR-0.6B938M0.55 GiB10apache-2.0
Fun-ASR-MLT-Nano-2512830M0.52 GiB6other
Fun-ASR-Nano-2512830M0.52 GiB9other
parakeet-tdt-1.1b1.1B0.64 GiB8cc-by-4.0
nemotron-speech-streaming-en-0.6b618M0.44 GiB6other
parakeet-ctc-1.1b1.1B0.76 GiB6cc-by-4.0

More permissively licensed

licences that allow commercial use
ModelParamsSmallestQuantsLicence
parakeet-unified-en-0.6b618M0.44 GiB6cc-by-4.0
cohere-transcribe-03-20262.1B1.41 GiB11apache-2.0
parakeet-tdt-0.6b-v3627M0.39 GiB10cc-by-4.0
whisper-medium764M0.25 GiB19apache-2.0
Voxtral-Mini-4B-Realtime-26024.4B2.35 GiB8apache-2.0
whisper-large-v31.5B0.49 GiB18apache-2.0
canary-180m-flash189M0.13 GiB6cc-by-4.0
whisper-large-v3-turbo809M0.27 GiB31apache-2.0