NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 vs Ornith-1.0-35B-FP8

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

nvidia · A · Open weights

Params

67.2 B

Context

262,144

30d

445 K

ornith-ai · B · Open weights

Params

35.1 B

Context

—

30d

233 K

mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4	Ornith-1.0-35B-FP8
Parameters	67.2 B	35.1 B
Architecture	NemotronHForCausalLM	Qwen3_5MoeForConditionalGeneration
Context length	262,144	—
Licence	other	mit
Commercial use	Unknown	Allowed
Languages	7	—
Downloads 30d	445,133	232,686
Downloads all time	10.8 M	2.2 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-03-10	2026-06-26

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

2.6 M211 K

NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Ornith-1.0-35B-FP8

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

Ornith-1.0-35B-FP8 · fp16 47.2 GB / 24 GB

❌ Won’t fit

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

❌ Won’t fit