Qwen3.6-35B-A3B-NVFP4 vs gemma-4-31B-it-NVFP4-turbo
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | gemma-4-31B-it-NVFP4-turbo |
|---|---|---|
| Parameters | 18.7 B | 32.5 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | Gemma4ForCausalLM |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 8,020,372 | 560,752 |
| Downloads all time | 34.6 M | 2.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2026-04-07 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
12.6 M273 K
Qwen3.6-35B-A3B-NVFP4
gemma-4-31B-it-NVFP4-turbo
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gemma-4-31B-it-NVFP4-turbo · fp16
26.6 GB / 24 GB
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB