Qwen3-4B vs SmolLM2-1.7B-Instruct

Specs, VRAM requirements and download trends — updated 21 September 2026.

Qwen · A
Params
4.0 B
Context
40,960
30d
6.9 M
apache-2.0 · commercial OK
HuggingFaceTB · B
Params
1.7 B
Context
8,192
30d
247 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-4B SmolLM2-1.7B-Instruct
Parameters 4.0 B 1.7 B
Architecture Qwen3ForCausalLM LlamaForCausalLM
Context length 40,960 8,192
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1
Downloads 30d 6,941,310 247,483
Downloads all time 80.5 M 2.9 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2024-10-31

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

7.3 M168 K
Qwen3-4B SmolLM2-1.7B-Instruct

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

SmolLM2-1.7B-Instruct · fp16 4.5 GB / 24 GB
✅ Runs comfortably
Qwen3-4B · fp16 10.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons