Voxtral-Mini-4B-Realtime-2602 vs wav2vec2-large-xlsr-53-japanese
Specs, VRAM requirements and download trends — updated 10 November 2026.
mistralai · A · Open weights
Params
4.4 B
Context
—
30d
1.5 M
apache-2.0 · commercial OK
jonatasgrosman · B · Open weights
Params
—
Context
—
30d
16.2 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Voxtral-Mini-4B-Realtime-2602 | wav2vec2-large-xlsr-53-japanese |
|---|---|---|
| Parameters | 4.4 B | — |
| Architecture | VoxtralRealtimeForConditionalGeneration | Wav2Vec2ForCTC |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 13 | 1 |
| Downloads 30d | 1,453,613 | 16,184,839 |
| Downloads all time | 14.6 M | 127.3 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2026-01-21 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
17.9 M1.4 M
Voxtral-Mini-4B-Realtime-2602
wav2vec2-large-xlsr-53-japanese
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Voxtral-Mini-4B-Realtime-2602 · fp16
20.7 GB / 24 GB
Adjacent comparisons
whisperkit-coreml vs wav2vec2-large-xlsr-53-japanese
speaker-diarization-3.1 vs wav2vec2-large-xlsr-53-japanese
faster-whisper-small vs wav2vec2-large-xlsr-53-japanese
whisper-large-v3-turbo vs wav2vec2-large-xlsr-53-japanese
speaker-diarization-community-1 vs wav2vec2-large-xlsr-53-japanese
whisper-base vs wav2vec2-large-xlsr-53-japanese