Qwen2.5-3B-Instruct vs SmolLM3-3B-Base
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-3B-Instruct | SmolLM3-3B-Base |
|---|---|---|
| Parameters | 3.1 B | 3.1 B |
| Architecture | Qwen2ForCausalLM | SmolLM3ForCausalLM |
| Context length | 32,768 | 65,536 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 1 | 8 |
| Downloads 30d | 4,751,814 | 614,531 |
| Downloads all time | 120.0 M | 1.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2025-06-19 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
7.6 M157 K
Qwen2.5-3B-Instruct
SmolLM3-3B-Base
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
SmolLM3-3B-Base · fp16
7.7 GB / 24 GB
Qwen2.5-3B-Instruct · fp16
7.8 GB / 24 GB