NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 vs Qwen3-235B-A22B-NVFP4

Specs, VRAM requirements and download trends — updated 14 August 2026.

nvidia · A · Open weights

Params

67.2 B

Context

262,144

30d

445 K

nvidia · B · Open weights

Params

132.8 B

Context

40,960

30d

167 K

apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4	Qwen3-235B-A22B-NVFP4
Parameters	67.2 B	132.8 B
Architecture	NemotronHForCausalLM	Qwen3MoeForCausalLM
Context length	262,144	40,960
Licence	other	apache-2.0
Commercial use	Unknown	Allowed
Languages	7	—
Downloads 30d	445,133	166,513
Downloads all time	10.8 M	260 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-03-10	2025-07-08

Daily snapshots, last 90 days (13 Aug – 10 Nov)

2.6 M167 K

NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Qwen3-235B-A22B-NVFP4

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

Qwen3-235B-A22B-NVFP4 · fp16 168.0 GB / 24 GB

❌ Won’t fit

NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 · fp16 @ 256K ctx 411.6 GB / 24 GB

❌ Won’t fit