Qwen2.5-VL-3B-Instruct vs Qwen3-VL-30B-A3B-Instruct-FP8
Specs, VRAM requirements and download trends — updated 16 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-VL-3B-Instruct | Qwen3-VL-30B-A3B-Instruct-FP8 |
|---|---|---|
| Parameters | 3.8 B | 31.1 B |
| Architecture | Qwen2_5_VLForConditionalGeneration | Qwen3VLMoeForConditionalGeneration |
| Context length | 128,000 | — |
| Licence | — | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 1 | — |
| Downloads 30d | 2,358,263 | 800,693 |
| Downloads all time | 102.2 M | 3.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-01-26 | 2025-10-01 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
8.2 M801 K
Qwen2.5-VL-3B-Instruct
Qwen3-VL-30B-A3B-Instruct-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-VL-3B-Instruct · fp16 @ 125K ctx
17.5 GB / 24 GB
Qwen3-VL-30B-A3B-Instruct-FP8 · fp16
40.6 GB / 24 GB