gpt2 vs SmolLM2-135M
Specs, VRAM requirements and download trends — updated 20 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt2 | SmolLM2-135M |
|---|---|---|
| Parameters | 140 M | 130 M |
| Architecture | GPT2LMHeadModel | LlamaForCausalLM |
| Context length | — | 8,192 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 15,362,811 | 2,105,264 |
| Downloads all time | 925.8 M | 20.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2024-10-31 |
Download trend
Daily snapshots, last 55 days (28 Jul – 20 Sep)
15.6 M1.7 M
gpt2
SmolLM2-135M
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
SmolLM2-135M · fp16
0.8 GB / 24 GB
gpt2 · fp16
1.1 GB / 24 GB