SmolLM2-135M-Instruct vs pythia-70m-deduped
Specs, VRAM requirements and download trends — updated 10 November 2026.
HuggingFaceTB · A · Open weights
Params
130 M
Context
8,192
30d
847 K
apache-2.0 · commercial OK
EleutherAI · B · Open weights
Params
100 M
Context
2,048
30d
729 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | SmolLM2-135M-Instruct | pythia-70m-deduped |
|---|---|---|
| Parameters | 130 M | 100 M |
| Architecture | LlamaForCausalLM | GPTNeoXForCausalLM |
| Context length | 8,192 | 2,048 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 847,496 | 728,542 |
| Downloads all time | 17.4 M | 17.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-10-31 | 2023-02-13 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.9 M729 K
SmolLM2-135M-Instruct
pythia-70m-deduped
A overtook B on 7 Nov
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
pythia-70m-deduped · fp16
0.7 GB / 24 GB
SmolLM2-135M-Instruct · fp16
0.8 GB / 24 GB