DeepSeek-V4-Flash vs NVIDIA-Nemotron-3-Super-120B-A12B-BF16

Specs, VRAM requirements and download trends — updated 10 November 2026.

deepseek-ai · A · Open weights

Params

158.1 B

Context

1,048,576

30d

1.2 M

mit · commercial OK

nvidia · B · Open weights

Params

123.6 B

Context

262,144

30d

1.0 M

Specification comparison

Differences are highlighted; identical values are muted.

Specification	DeepSeek-V4-Flash	NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Deployment	Open weights · also via API	Open weights
Parameters	158.1 B	123.6 B
Architecture	DeepseekV4ForCausalLM	NemotronHForCausalLM
Context length	1,048,576	262,144
Licence	mit	other
Commercial use	Allowed	Unknown
Languages	—	7
Downloads 30d	1,151,336	1,042,412
Downloads all time	13.7 M	7.7 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-04-22	2026-03-10
API input price / 1M tokens	$0.091	not on OpenRouter
API output price / 1M tokens	$0.18	not on OpenRouter
Est. cost per 1M input + 1M output tokens	$0.27	not on OpenRouter
Cached input / 1M tokens	$0.018	not on OpenRouter
AA Intelligence Index	—	not on OpenRouter
AA Coding Index	56.2	not on OpenRouter
AA Agentic Index	22.2	not on OpenRouter
Max output tokens	943,717	not on OpenRouter
API providers	13	not on OpenRouter
Tool calling	Yes	not on OpenRouter
Reasoning mode	Yes	not on OpenRouter