Gemma-4-31B-IT-NVFP4 vs Qwen-72B
Specs, VRAM requirements and download trends — updated 5 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Gemma-4-31B-IT-NVFP4 | Qwen-72B |
|---|---|---|
| Parameters | 20.9 B | 72.3 B |
| Architecture | Gemma4ForConditionalGeneration | QWenLMHeadModel |
| Context length | — | 32,768 |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | — | 2 |
| Downloads 30d | 921,928 | 157,322 |
| Downloads all time | 13.5 M | 7.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-02 | 2023-11-26 |
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
4.2 M157 K
Gemma-4-31B-IT-NVFP4
Qwen-72B
A overtook B on 4 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Gemma-4-31B-IT-NVFP4 · fp16
39.5 GB / 24 GB
Qwen-72B · fp16
170.4 GB / 24 GB