granite-4.1-8b vs CodeLlama-7b-hf
Specs, VRAM requirements and download trends — updated 30 August 2026.
ibm-granite · A · Open weights
Params
8.8 B
Context
131,072
30d
192 K
apache-2.0 · commercial OK
codellama · B · Open weights
Params
6.7 B
Context
16,384
30d
151 K
llama2 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | granite-4.1-8b | CodeLlama-7b-hf |
|---|---|---|
| Parameters | 8.8 B | 6.7 B |
| Architecture | GraniteForCausalLM | LlamaForCausalLM |
| Context length | 131,072 | 16,384 |
| Licence | apache-2.0 | llama2 |
| Commercial use | Allowed | Conditional |
| Languages | — | 1 |
| Downloads 30d | 192,200 | 150,591 |
| Downloads all time | 6.1 M | 4.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-06 | 2023-08-24 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.2 M151 K
granite-4.1-8b
CodeLlama-7b-hf
A overtook B on 5 Nov
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
CodeLlama-7b-hf · fp16
16.3 GB / 24 GB
granite-4.1-8b · fp16 @ 128K ctx
40.9 GB / 24 GB