speaker-diarization-3.1 vs Phi-4-multimodal-instruct

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

pyannote · A
Params
Context
30d
8.9 M
mit · commercial OK
microsoft · B
Params
5.6 B
Context
131,072
30d
572 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification speaker-diarization-3.1 Phi-4-multimodal-instruct
Parameters 5.6 B
Architecture Phi4MMForCausalLM
Context length 131,072
Licence mit mit
Commercial use Allowed Allowed
Languages 24
Downloads 30d 8,909,178 571,625
Downloads all time 333.7 M 8.3 M
Quantizations on the Hub SAFETENSORS
Gated Yes — accept licence No
First seen on the Hub 2023-11-16 2025-02-24

Download trend

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

8.9 M539 K
speaker-diarization-3.1 Phi-4-multimodal-instruct

VRAM side by side

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

Phi-4-multimodal-instruct · fp16 @ 128K ctx 28.0 GB / 24 GB
❌ Won’t fit

Adjacent comparisons