granite-4.1-8b vs Qwen2.5-Coder-7B-Instruct-GPTQ-Int4
Specs, VRAM requirements and download trends — updated 6 August 2026.
Qwen · B
Params
7.6 B
Context
32,768
30d
536 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | granite-4.1-8b | Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 |
|---|---|---|
| Parameters | 8.8 B | 7.6 B |
| Architecture | GraniteForCausalLM | Qwen2ForCausalLM |
| Context length | 131,072 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 4,208,265 | 535,728 |
| Downloads all time | 5.0 M | 6.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-06 | 2024-09-20 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
4.2 M506 K
granite-4.1-8b
Qwen2.5-Coder-7B-Instruct-GPTQ-Int4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 · fp16
7.8 GB / 24 GB
granite-4.1-8b · fp16 @ 128K ctx
40.9 GB / 24 GB