granite-4.1-8b vs gpt-neox-20b
Specs, VRAM requirements and download trends — updated 15 August 2026.
ibm-granite · A · Open weights
Params
8.8 B
Context
131,072
30d
192 K
apache-2.0 · commercial OK
EleutherAI · B · Open weights
Params
20.7 B
Context
2,048
30d
259 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | granite-4.1-8b | gpt-neox-20b |
|---|---|---|
| Parameters | 8.8 B | 20.7 B |
| Architecture | GraniteForCausalLM | GPTNeoXForCausalLM |
| Context length | 131,072 | 2,048 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 192,200 | 259,261 |
| Downloads all time | 6.1 M | 6.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-06 | 2022-04-07 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.2 M192 K
granite-4.1-8b
gpt-neox-20b
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
granite-4.1-8b · fp16 @ 128K ctx
40.9 GB / 24 GB
gpt-neox-20b · fp16
49.0 GB / 24 GB