NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 vs Kimi-K2-Thinking-NVFP4

Specs, VRAM requirements and download trends — updated 25 October 2026.

nvidia · A · Open weights

Params

560.5 B

Context

262,144

30d

1.1 M

nvidia · B · Open weights

Params

519.1 B

Context

262,144

30d

229 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16	Kimi-K2-Thinking-NVFP4
Deployment	Open weights · also via API	Open weights
Parameters	560.5 B	519.1 B
Architecture	NemotronHForCausalLM	DeepseekV3ForCausalLM
Context length	262,144	262,144
Licence	other	other
Commercial use	Unknown	Unknown
Languages	12	—
Downloads 30d	1,133,423	228,965
Downloads all time	2.2 M	652 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-06-03	2025-12-02
API input price / 1M tokens	$0.60	not on OpenRouter
API output price / 1M tokens	$2.40	not on OpenRouter
Est. cost per 1M input + 1M output tokens	$3.00	not on OpenRouter
Cached input / 1M tokens	$0.12	not on OpenRouter
AA Intelligence Index	22.9	not on OpenRouter
AA Coding Index	49.3	not on OpenRouter
AA Agentic Index	20.1	not on OpenRouter
Max output tokens	182,520	not on OpenRouter
API providers	3	not on OpenRouter
Tool calling	Yes	not on OpenRouter
Reasoning mode	Yes	not on OpenRouter