Qwen3.5-2B vs Qwen3-VL-2B-Instruct
Specs, VRAM requirements and download trends — updated 10 November 2026.
Qwen · B · Open weights
Params
2.1 B
Context
—
30d
1.1 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.5-2B | Qwen3-VL-2B-Instruct |
|---|---|---|
| Parameters | 2.3 B | 2.1 B |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3VLForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 3,743,248 | 1,091,858 |
| Downloads all time | 22.3 M | 219.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-28 | 2025-10-19 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.9 M1.1 M
Qwen3.5-2B
Qwen3-VL-2B-Instruct
A overtook B on 9 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-VL-2B-Instruct · fp16
5.5 GB / 24 GB
Qwen3.5-2B · fp16
5.8 GB / 24 GB