Models
Deduplicated to base models. Quantizations are an attribute, not a separate page.
| Model | Publisher | Params | Quants | Range | Downloads |
|---|---|---|---|---|---|
| nemotron-3.5-asr-streaming-0.6b | nvidia | 638M | 8 | 0.38 GiB – 2.38 GiB | 2.0M |
| parakeet-unified-en-0.6b | nvidia | 618M | 6 | 0.44 GiB – 2.30 GiB | 1.8M |
| cohere-transcribe-03-2026 | CohereLabs | 2.1B | 11 | 1.41 GiB – 3.82 GiB | 996k |
| parakeet-tdt-0.6b-v3 | nvidia | 627M | 10 | 0.39 GiB – 2.34 GiB | 668k |
| whisper-medium | openai | 764M | 19 | 0.25 GiB – 2.85 GiB | 541k |
| Voxtral-Mini-4B-Realtime-2602 | mistralai | 4.4B | 8 | 2.35 GiB – 8.27 GiB | 402k |
| whisper-large-v3 | openai | 1.5B | 18 | 0.49 GiB – 2.89 GiB | 307k |
| canary-180m-flash | nvidia | 189M | 6 | 0.13 GiB – 0.70 GiB | 275k |
| whisper-large-v3-turbo | openai | 809M | 31 | 0.27 GiB – 1.51 GiB | 264k |
| Qwen3-ASR-1.7B | Qwen | 2.3B | 13 | 1.23 GiB – 4.38 GiB | 184k |
| Voxtral-Small-24B-2507 | mistralai | 24.3B | 31 | 6.71 GiB – 45.21 GiB | 164k |
| Qwen3-ASR-0.6B | Qwen | 938M | 10 | 0.55 GiB – 1.47 GiB | 142k |
| parakeet-tdt-0.6b-v2 | nvidia | 618M | 8 | 0.37 GiB – 2.30 GiB | 110k |
| GigaAM-v3 | ai-sage | 223M | 18 | 0.17 GiB – 0.83 GiB | 102k |
| canary-1b-v2 | nvidia | 980M | 12 | 0.37 GiB – 3.65 GiB | 87k |
| parakeet-ctc-0.6b | nvidia | 609M | 11 | 0.44 GiB – 16.13 GiB | 44k |
| granite-speech-4.1-2b-nar | ibm-granite | 2.3B | 8 | 1.45 GiB – 5.36 GiB | 42k |
| whisper-small | openai | 242M | 19 | 0.08 GiB – 0.90 GiB | 42k |
| granite-speech-4.1-2b | ibm-granite | 2.3B | 13 | 1.06 GiB – 5.20 GiB | 41k |
| whisper-large | openai | 1.5B | 6 | 0.93 GiB – 5.75 GiB | 39k |
| Fun-ASR-MLT-Nano-2512 | FunAudioLLM | 830M | 6 | 0.52 GiB – 1.55 GiB | 36k |
| Voxtral-Mini-3B-2507 | mistralai | 4.7B | 31 | 1.45 GiB – 8.73 GiB | 34k |
| canary-1b-flash | nvidia | 811M | 6 | 0.63 GiB – 3.32 GiB | 31k |
| whisper-large-v2 | openai | 1.5B | 6 | 0.93 GiB – 5.75 GiB | 27k |
| Fun-ASR-Nano-2512 | FunAudioLLM | 830M | 9 | 0.52 GiB – 1.84 GiB | 23k |
| canary-qwen-2.5b | nvidia | 2.6B | 9 | 1.62 GiB – 5.31 GiB | 22k |
| parakeet-tdt-1.1b | nvidia | 1.1B | 8 | 0.64 GiB – 3.99 GiB | 21k |
| SenseVoiceSmall | FunAudioLLM | 234M | 9 | 0.13 GiB – 0.87 GiB | 20k |
| granite-speech-4.1-2b-plus | ibm-granite | 2.1B | 13 | 0.95 GiB – 5.21 GiB | 20k |
| Breeze-ASR-25 | MediaTek-Research | 1.5B | 6 | 0.93 GiB – 2.89 GiB | 16k |
| nemotron-speech-streaming-en-0.6b | nvidia | 618M | 6 | 0.44 GiB – 2.30 GiB | 15k |
| granite-4.0-1b-speech | ibm-granite | 2.3B | 6 | 1.49 GiB – 4.31 GiB | 14k |
| parakeet-ctc-1.1b | nvidia | 1.1B | 6 | 0.76 GiB – 3.96 GiB | 11k |
| parakeet-rnnt-1.1b | nvidia | 1.1B | 8 | 0.64 GiB – 3.99 GiB | 11k |
| canary-1b | nvidia | 1.0B | 6 | 0.68 GiB – 3.81 GiB | 11k |
| whisper-base | openai | 73M | 19 | 0.03 GiB – 0.27 GiB | 11k |
| moonshine-streaming-medium | UsefulSensors | 266M | 3 | 0.28 GiB – 0.99 GiB | 10k |
| whisper-medium.en | openai | 764M | 6 | 0.47 GiB – 2.85 GiB | 10k |
| parakeet-rnnt-0.6b | nvidia | 617M | 8 | 0.37 GiB – 2.30 GiB | 9k |
| parakeet-tdt_ctc-1.1b | nvidia | 1.1B | 8 | 0.64 GiB – 3.99 GiB | 7k |
| whisper-small.en | openai | 242M | 6 | 0.16 GiB – 0.90 GiB | 7k |
| moonshine-streaming-small | UsefulSensors | 140M | 3 | 0.18 GiB – 0.52 GiB | 7k |
| whisper-tiny | openai | 38M | 18 | 0.02 GiB – 0.14 GiB | 6k |
| MOSS-Transcribe-Diarize | OpenMOSS-Team | 909M | 11 | 0.50 GiB – 3.39 GiB | 6k |
| parakeet-tdt_ctc-110m | nvidia | 114M | 8 | 0.07 GiB – 0.43 GiB | 5k |
| GLM-ASR-Nano-2512 | zai-org | 2.3B | 5 | 0.91 GiB – 2.97 GiB | 5k |
| ARK-ASR-3B | AutoArk-AI | 4.1B | 3 | 3.28 GiB – 6.99 GiB | 2k |
| whisper-base.en | openai | 73M | 6 | 0.05 GiB – 0.27 GiB | 2k |
| moonshine-streaming-tiny | UsefulSensors | 44M | 4 | 0.03 GiB – 0.17 GiB | 2k |
| moonshine-base | UsefulSensors | 62M | 5 | 0.04 GiB – 0.23 GiB | 2k |
| Qwen3-ForcedAligner-0.6B | Qwen | 918M | 4 | 0.49 GiB – 1.72 GiB | 2k |
| VibeVoice-Large | microsoft | 9.3B | 7 | 5.74 GiB – 17.41 GiB | 2k |