Qwen3-4B vs Qwen2.5-14B-Instruct-AWQ
Specs, VRAM requirements and download trends — updated 23 October 2026.
Qwen · B · Open weights
Params
14.8 B
Context
32,768
30d
1.4 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-4B | Qwen2.5-14B-Instruct-AWQ |
|---|---|---|
| Parameters | 4.0 B | 14.8 B |
| Architecture | Qwen3ForCausalLM | Qwen2ForCausalLM |
| Context length | 40,960 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 11,578,451 | 1,400,083 |
| Downloads all time | 92.7 M | 17.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2024-09-17 |
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
12.6 M1.4 M
Qwen3-4B
Qwen2.5-14B-Instruct-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-4B · fp16
10.0 GB / 24 GB
Qwen2.5-14B-Instruct-AWQ · fp16
13.7 GB / 24 GB