Phi-3.5-mini-instruct vs VLM2Vec-Full

Specs, VRAM requirements and download trends — updated 2 August 2026.

microsoft · A · Open weights
Params
3.8 B
Context
131,072
30d
376 K
mit · commercial OK
TIGER-Lab · B · Open weights
Params
4.2 B
Context
131,072
30d
199 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Phi-3.5-mini-instruct VLM2Vec-Full
Parameters 3.8 B 4.2 B
Architecture Phi3ForCausalLM Phi3VForCausalLM
Context length 131,072 131,072
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages 1 1
Downloads 30d 375,768 199,363
Downloads all time 13.1 M 2.8 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-08-16 2024-10-08

Download trend

Daily snapshots, last 90 days (28 Jul – 25 Oct)

1.2 M199 K
Phi-3.5-mini-instruct VLM2Vec-Full

VRAM side by side

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

Phi-3.5-mini-instruct · fp16 @ 128K ctx 18.1 GB / 24 GB
✅ Runs comfortably
VLM2Vec-Full · fp16 @ 128K ctx 19.6 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons