Alternatives to Voxtral-Mini-4B-Realtime-2602
Voxtral-Mini-4B-Realtime-2602 alternatives
Voxtral-Mini-4B-Realtime-2602's smallest published quantization is 2.35 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
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| nemotron-3.5-asr-streaming-0.6b | 638M | 0.38 GiB | 8 | other |
| parakeet-unified-en-0.6b | 618M | 0.44 GiB | 6 | cc-by-4.0 |
| cohere-transcribe-03-2026 | 2.1B | 1.41 GiB | 11 | apache-2.0 |
| parakeet-tdt-0.6b-v3 | 627M | 0.39 GiB | 10 | cc-by-4.0 |
| whisper-medium | 764M | 0.25 GiB | 19 | apache-2.0 |
| whisper-large-v3 | 1.5B | 0.49 GiB | 18 | apache-2.0 |
| canary-180m-flash | 189M | 0.13 GiB | 6 | cc-by-4.0 |
| whisper-large-v3-turbo | 809M | 0.27 GiB | 31 | apache-2.0 |
Comparable in size
within ±40%, so a like-for-like swap
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| ARK-ASR-3B | 4.1B | 3.28 GiB | 3 | other |
More permissively licensed
licences that allow commercial use
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| parakeet-unified-en-0.6b | 618M | 0.44 GiB | 6 | cc-by-4.0 |
| cohere-transcribe-03-2026 | 2.1B | 1.41 GiB | 11 | apache-2.0 |
| parakeet-tdt-0.6b-v3 | 627M | 0.39 GiB | 10 | cc-by-4.0 |
| whisper-medium | 764M | 0.25 GiB | 19 | apache-2.0 |
| whisper-large-v3 | 1.5B | 0.49 GiB | 18 | apache-2.0 |
| canary-180m-flash | 189M | 0.13 GiB | 6 | cc-by-4.0 |
| whisper-large-v3-turbo | 809M | 0.27 GiB | 31 | apache-2.0 |
| Qwen3-ASR-1.7B | 2.3B | 1.23 GiB | 13 | apache-2.0 |