whisper-large-v3 vs whisper-bemba-stt
Specs, VRAM requirements and download trends — updated 28 July 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | whisper-large-v3 | whisper-bemba-stt |
|---|---|---|
| Parameters | 1.5 B | 240 M |
| Architecture | WhisperForConditionalGeneration | WhisperForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | 99 | — |
| Downloads 30d | 5,497,354 | 546,341 |
| Downloads all time | 139.4 M | 1.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-11-07 | 2026-01-13 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
6.0 M534 K
whisper-large-v3
whisper-bemba-stt
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
whisper-bemba-stt · fp16
1.6 GB / 24 GB
whisper-large-v3 · fp16
10.9 GB / 24 GB