distilgpt2 vs gpt-neo-125m
Specs, VRAM requirements and download trends — updated 10 November 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | distilgpt2 | gpt-neo-125m |
|---|---|---|
| Parameters | 90 M | 150 M |
| Architecture | GPT2LMHeadModel | GPTNeoForCausalLM |
| Context length | — | 2,048 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 1,481,788 | 458,223 |
| Downloads all time | 259.1 M | 11.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2022-03-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.5 M347 K
distilgpt2
gpt-neo-125m
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
distilgpt2 · fp16
0.9 GB / 24 GB
gpt-neo-125m · fp16
1.1 GB / 24 GB