gpt2 vs SmolLM-135M-Instruct-FP32
Specs, VRAM requirements and download trends — updated 25 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt2 | SmolLM-135M-Instruct-FP32 |
|---|---|---|
| Parameters | 140 M | 135 M |
| Architecture | GPT2LMHeadModel | LlamaForCausalLM |
| Context length | — | 2,048 |
| Licence | mit | — |
| Commercial use | Allowed | Unknown |
| Languages | 1 | — |
| Downloads 30d | 20,107,244 | 143,038 |
| Downloads all time | 948.8 M | 313 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2025-07-31 |
Download trend
90 days of snapshots recorded — chart in 0 days.
948.8 M
gpt2 · all-time downloads
313 K
SmolLM-135M-Instruct-FP32 · all-time downloads
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gpt2 · fp16
1.1 GB / 24 GB
SmolLM-135M-Instruct-FP32 · fp16
1.1 GB / 24 GB