SmolLM2-135M-Instruct vs SmolLM2-135M

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

HuggingFaceTB · A
Params
130 M
Context
8,192
30d
1.5 M
apache-2.0 · commercial OK
HuggingFaceTB · B
Params
130 M
Context
8,192
30d
2.0 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification SmolLM2-135M-Instruct SmolLM2-135M
Parameters 130 M 130 M
Architecture LlamaForCausalLM LlamaForCausalLM
Context length 8,192 8,192
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1 1
Downloads 30d 1,535,908 1,977,502
Downloads all time 15.4 M 20.6 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-10-31 2024-10-31

Download trend

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

2.6 M1.3 M
SmolLM2-135M-Instruct SmolLM2-135M

VRAM side by side

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

SmolLM2-135M-Instruct · fp16 0.8 GB / 24 GB
✅ Runs comfortably
SmolLM2-135M · fp16 0.8 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons