Florence-2-base vs Qwen2.5-VL-3B-Instruct-AWQ
Specs, VRAM requirements and download trends — updated 2 November 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Florence-2-base | Qwen2.5-VL-3B-Instruct-AWQ |
|---|---|---|
| Parameters | 230 M | 3.8 B |
| Architecture | Florence2ForConditionalGeneration | Qwen2_5_VLForConditionalGeneration |
| Context length | — | 128,000 |
| Licence | mit | — |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 11,733,723 | 867,836 |
| Downloads all time | 37.3 M | 4.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-06-15 | 2025-02-13 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
11.7 M867 K
Florence-2-base
Qwen2.5-VL-3B-Instruct-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Florence-2-base · fp16
1.0 GB / 24 GB
Qwen2.5-VL-3B-Instruct-AWQ · fp16 @ 125K ctx
13.0 GB / 24 GB