Qwen3-4B-Instruct-2507 vs Qwen2.5-Coder-3B-Instruct
Specs, VRAM requirements and download trends — updated 20 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-4B-Instruct-2507 | Qwen2.5-Coder-3B-Instruct |
|---|---|---|
| Parameters | 4.0 B | 3.1 B |
| Architecture | Qwen3ForCausalLM | Qwen2ForCausalLM |
| Context length | 262,144 | 32,768 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 4,024,479 | 599,149 |
| Downloads all time | 61.6 M | 3.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-08-05 | 2024-11-06 |
Download trend
Daily snapshots, last 55 days (28 Jul – 20 Sep)
4.0 M179 K
Qwen3-4B-Instruct-2507
Qwen2.5-Coder-3B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-3B-Instruct · fp16
7.8 GB / 24 GB
Qwen3-4B-Instruct-2507 · fp16 @ 256K ctx
28.6 GB / 24 GB