granite-4.1-8b vs diffusiongemma-26B-A4B-it-NVFP4
Specs, VRAM requirements and download trends — updated 21 August 2026.
nvidia · B
Params
14.4 B
Context
—
30d
232 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | granite-4.1-8b | diffusiongemma-26B-A4B-it-NVFP4 |
|---|---|---|
| Parameters | 8.8 B | 14.4 B |
| Architecture | GraniteForCausalLM | DiffusionGemmaForBlockDiffusion |
| Context length | 131,072 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 217,938 | 232,025 |
| Downloads all time | 6.1 M | 3.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-06 | 2026-06-10 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
4.3 M207 K
granite-4.1-8b
diffusiongemma-26B-A4B-it-NVFP4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
diffusiongemma-26B-A4B-it-NVFP4 · fp16
23.4 GB / 24 GB
granite-4.1-8b · fp16 @ 128K ctx
40.9 GB / 24 GB