pythia-160m vs SmolLM-135M-Instruct-FP32
Specs, VRAM requirements and download trends — updated 25 October 2026.
EleutherAI · A · Open weights
Params
210 M
Context
2,048
30d
3.4 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | pythia-160m | SmolLM-135M-Instruct-FP32 |
|---|---|---|
| Parameters | 210 M | 135 M |
| Architecture | GPTNeoXForCausalLM | LlamaForCausalLM |
| Context length | 2,048 | 2,048 |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | 1 | — |
| Downloads 30d | 3,397,668 | 143,038 |
| Downloads all time | 30.2 M | 313 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-02-08 | 2025-07-31 |
Download trend
90 days of snapshots recorded — chart in 0 days.
30.2 M
pythia-160m · 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
pythia-160m · fp16
0.9 GB / 24 GB
SmolLM-135M-Instruct-FP32 · fp16
1.1 GB / 24 GB