gpt-oss-120b vs NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

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

openai · A
Params
120.4 B
Context
131,072
30d
4.2 M
apache-2.0 · commercial OK
nvidia · B
Params
335.0 B
Context
262,144
30d
233 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification gpt-oss-120b NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Parameters 120.4 B 335.0 B
Architecture GptOssForCausalLM NemotronHForCausalLM
Context length 131,072 262,144
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages 12
Downloads 30d 4,221,708 233,194
Downloads all time 48.6 M 757 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-08-04 2026-06-03

Download trend

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

4.3 M233 K
gpt-oss-120b NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

VRAM side by side

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

gpt-oss-120b · fp16 @ 128K ctx 433.0 GB / 24 GB
❌ Won’t fit
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 · fp16 @ 256K ctx 1,996.2 GB / 24 GB
❌ Won’t fit

Adjacent comparisons