Qwen3.5-0.8B vs Florence-2-base

Specs, VRAM requirements and download trends — updated 10 November 2026.

Qwen · A · Open weights

Params

870 M

Context

—

30d

3.5 M

apache-2.0 · commercial OK

microsoft · B · Open weights

Params

230 M

Context

—

30d

11.7 M

mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3.5-0.8B	Florence-2-base
Parameters	870 M	230 M
Architecture	Qwen3_5ForConditionalGeneration	Florence2ForConditionalGeneration
Context length	—	—
Licence	apache-2.0	mit
Commercial use	Allowed	Allowed
Languages	—	—
Downloads 30d	3,549,829	11,733,723
Downloads all time	23.7 M	37.3 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-02-28	2024-06-15

Daily snapshots, last 90 days (13 Aug – 10 Nov)

11.7 M2.3 M

Qwen3.5-0.8B Florence-2-base

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

Florence-2-base · fp16 1.0 GB / 24 GB

✅ Runs comfortably

Qwen3.5-0.8B · fp16 2.6 GB / 24 GB

✅ Runs comfortably