speaker-diarization-3.1 vs Voxtral-Mini-4B-Realtime-2602

Specs, VRAM requirements and download trends — updated 6 August 2026.

pyannote · A
Params
Context
30d
8.9 M
mit · commercial OK
mistralai · B
Params
4.4 B
Context
30d
2.3 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification speaker-diarization-3.1 Voxtral-Mini-4B-Realtime-2602
Parameters 4.4 B
Architecture VoxtralRealtimeForConditionalGeneration
Context length
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages 13
Downloads 30d 8,909,178 2,268,420
Downloads all time 333.7 M 8.2 M
Quantizations on the Hub SAFETENSORS
Gated Yes — accept licence No
First seen on the Hub 2023-11-16 2026-01-21

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

8.9 M2.0 M
speaker-diarization-3.1 Voxtral-Mini-4B-Realtime-2602

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Voxtral-Mini-4B-Realtime-2602 · fp16 20.7 GB / 24 GB
⚠️ Tight — reduce context

Adjacent comparisons