SmolLM2-135M vs llama-160m

Specs, VRAM requirements and download trends — updated 6 August 2026.

HuggingFaceTB · A
Params
130 M
Context
8,192
30d
1.8 M
apache-2.0 · commercial OK
JackFram · B
Params
160 M
Context
2,048
30d
251 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification SmolLM2-135M llama-160m
Parameters 130 M 160 M
Architecture LlamaForCausalLM LlamaForCausalLM
Context length 8,192 2,048
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1 1
Downloads 30d 1,824,932 251,368
Downloads all time 17.0 M 4.8 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-10-31 2023-05-26

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

1.9 M246 K
SmolLM2-135M llama-160m

VRAM side by side

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

SmolLM2-135M · fp16 0.8 GB / 24 GB
✅ Runs comfortably
llama-160m · fp16 1.2 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons