NVIDIA-Nemotron-3-Super-120B-A12B-BF16 vs Devstral-2-123B-Instruct-2512

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

nvidia · A · Open weights

Params

123.6 B

Context

262,144

30d

978 K

mistralai · B · Open weights

Params

125.0 B

Context

262,144

30d

5 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Super-120B-A12B-BF16	Devstral-2-123B-Instruct-2512
Deployment	Open weights	Open weights · also via API
Parameters	123.6 B	125.0 B
Architecture	NemotronHForCausalLM	Ministral3ForCausalLM
Context length	262,144	262,144
Licence	other	other
Commercial use	Unknown	Unknown
Languages	7	—
Downloads 30d	978,022	5,315
Downloads all time	7.1 M	353 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-03-10	2025-11-28
API input price / 1M tokens	not on OpenRouter	$0.40
API output price / 1M tokens	not on OpenRouter	$2.00
Est. cost per 1M input + 1M output tokens	not on OpenRouter	$2.40
Cached input / 1M tokens	not on OpenRouter	$0.04
AA Intelligence Index	not on OpenRouter	8.6
AA Coding Index	not on OpenRouter	31.3
AA Agentic Index	not on OpenRouter	2.3
Max output tokens	not on OpenRouter	209,715
API providers	not on OpenRouter	1
Tool calling	not on OpenRouter	Yes
Reasoning mode	not on OpenRouter	No