NVIDIA-Nemotron-3-Super-120B-A12B-BF16 vs c4ai-command-a-03-2025

Specs, VRAM requirements and download trends — updated 24 October 2026.

nvidia · A · Open weights

Params

123.6 B

Context

262,144

30d

978 K

CohereLabs · B · Open weights

Params

111.1 B

Context

—

30d

1 K

cc-by-nc-4.0 · non-commercial

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Super-120B-A12B-BF16	c4ai-command-a-03-2025
Deployment	Open weights	Open weights · also via API
Parameters	123.6 B	111.1 B
Architecture	NemotronHForCausalLM	Cohere2ForCausalLM
Context length	262,144	256,000
Licence	other	cc-by-nc-4.0
Commercial use	Unknown	Not allowed
Languages	7	23
Downloads 30d	978,022	1,494
Downloads all time	7.1 M	126 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	Yes — accept licence
First seen on the Hub	2026-03-10	2025-03-11
API input price / 1M tokens	not on OpenRouter	$2.50
API output price / 1M tokens	not on OpenRouter	$10.00
Est. cost per 1M input + 1M output tokens	not on OpenRouter	$12.50
Cached input / 1M tokens	not on OpenRouter	—
AA Intelligence Index	not on OpenRouter	13.1
AA Coding Index	not on OpenRouter	27.8
AA Agentic Index	not on OpenRouter	1
Max output tokens	not on OpenRouter	8,192
API providers	not on OpenRouter	1
Tool calling	not on OpenRouter	No
Reasoning mode	not on OpenRouter	No