Qwen3.6-35B-A3B-FP8 vs gemma-4-31B-it-NVFP4

Specs, VRAM requirements and download trends — updated 6 August 2026.

Qwen · A
Params
36.0 B
Context
30d
8.9 M
apache-2.0 · commercial OK
RedHatAI · B
Params
32.7 B
Context
30d
1.2 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.6-35B-A3B-FP8 gemma-4-31B-it-NVFP4
Parameters 36.0 B 32.7 B
Architecture Qwen3_5MoeForConditionalGeneration Gemma4ForConditionalGeneration
Context length
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 8,946,336 1,221,887
Downloads all time 24.7 M 2.0 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-15 2026-04-03

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

8.9 M1.2 M
Qwen3.6-35B-A3B-FP8 gemma-4-31B-it-NVFP4

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

gemma-4-31B-it-NVFP4 · fp16 31.0 GB / 24 GB
❌ Won’t fit
Qwen3.6-35B-A3B-FP8 · fp16 47.1 GB / 24 GB
❌ Won’t fit

Adjacent comparisons