Qwen3-4B-Base vs Qwen3-1.7B-Base
Specs, VRAM requirements and download trends — updated 12 September 2026.
Qwen · B · Open weights
Params
1.7 B
Context
32,768
30d
573 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-4B-Base | Qwen3-1.7B-Base |
|---|---|---|
| Parameters | 4.0 B | 1.7 B |
| Architecture | Qwen3ForCausalLM | Qwen3ForCausalLM |
| Context length | 32,768 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 577,717 | 573,471 |
| Downloads all time | 23.2 M | 8.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-28 | 2025-04-28 |
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
2.0 M549 K
Qwen3-4B-Base
Qwen3-1.7B-Base
A overtook B on 20 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-1.7B-Base · fp16
4.5 GB / 24 GB
Qwen3-4B-Base · fp16
10.0 GB / 24 GB