Qwen3-VL-2B-Instruct vs Qwen3.5-2B-Base
Specs, VRAM requirements and download trends — updated 11 September 2026.
Qwen · A · Open weights
Params
2.1 B
Context
—
30d
1.9 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-VL-2B-Instruct | Qwen3.5-2B-Base |
|---|---|---|
| Parameters | 2.1 B | 2.3 B |
| Architecture | Qwen3VLForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 1,896,883 | 892,422 |
| Downloads all time | 219.2 M | 2.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-10-19 | 2026-02-28 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
3.1 M810 K
Qwen3-VL-2B-Instruct
Qwen3.5-2B-Base
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-Base · fp16
5.8 GB / 24 GB
Adjacent comparisons
Qwen3.5-4B vs Qwen3-VL-2B-Instruct
Qwen3.5-2B vs Qwen3-VL-2B-Instruct
Qwen3-VL-2B-Instruct vs Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF
Qwen3-VL-2B-Instruct vs Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen3-VL-2B-Instruct vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
Qwen3-VL-2B-Instruct vs Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF