NVIDIA-Nemotron-3-Super-120B-A12B-BF16 vs Mixtral-8x22B-Instruct-v0.1

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

140.6 B

Context

65,536

30d

46 K

apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Super-120B-A12B-BF16	Mixtral-8x22B-Instruct-v0.1
Deployment	Open weights	Open weights · also via API
Parameters	123.6 B	140.6 B
Architecture	NemotronHForCausalLM	MixtralForCausalLM
Context length	262,144	65,536
Licence	other	apache-2.0
Commercial use	Unknown	Allowed
Languages	7	5
Downloads 30d	978,022	46,472
Downloads all time	7.1 M	6.3 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-03-10	2024-04-16
API input price / 1M tokens	not on OpenRouter	$2.00
API output price / 1M tokens	not on OpenRouter	$6.00
Est. cost per 1M input + 1M output tokens	not on OpenRouter	$8.00
Cached input / 1M tokens	not on OpenRouter	$0.20
AA Intelligence Index	not on OpenRouter	5.7
AA Coding Index	not on OpenRouter	—
AA Agentic Index	not on OpenRouter	—
Max output tokens	not on OpenRouter	52,428
API providers	not on OpenRouter	1
Tool calling	not on OpenRouter	Yes
Reasoning mode	not on OpenRouter	No