Models | Jetson AI Lab

Nemotron 3.5 Bolt E4B 4GB

LLM

NVIDIA's compact conversational model for local assistants, multi-turn tool use, and interactive characters. Run text chat on Jetson with llama.cpp.

d1-3B

VLM

Liquid AI's zero-shot classification model for text and images, with a guide to running it on Jetson using PyTorch.

Qwen3.8 Flash Next

VLM

Qwen's vision-language MoE model for reasoning, coding, and tool use on Jetson Thor, with NVFP4 quantization and MTP speculative decoding

Filter by model name		Modules					Inference engines				Actions
Filter by model name		T5000	T4000	AGX Orin 64GB	Orin NX 16GB	Orin Nano 8GB	vLLM	Ollama	llama.cpp	TensorRT Edge-LLM	Actions
Nemotron 3.5 Bolt E4B 4GB New	NVIDIA Nemotron	✓	✓	✓	✓	✓	✓	—	✓	—
d1-3B New	Liquid AI d1	—	—	—	—	—	—	—	—	—
d1-omni-600M New	Liquid AI d1	—	—	—	—	—	—	—	—	—
FLUX 3 Action New	Black Forest Labs	—	—	—	—	—	—	—	—	—
Qwen3.8 Flash Next New	Alibaba Qwen3.8	✓	—	—	—	—	✓	—	—	—
Qwen3.8 27B New	Alibaba Qwen3.8	✓	✓	✓	—	—	✓	—	✓	—
Nemotron 3.5 Lightning New	NVIDIA Nemotron	✓	✓	✓	—	—	✓	—	✓	✓
Muse Glimmer 30B New	Meta Muse	✓	✓	✓	—	—	✓	—	✓	—
Nemotron3 Nano 4B New	NVIDIA Nemotron	✓	✓	✓	✓	✓	✓	—	✓	—
FunctionGemma New	Google Gemma3	✓	✓	✓	✓	✓	—	—	✓	—
Cosmos Reason 1 7B New	NVIDIA Cosmos	✓	✓	✓	✓	✓	✓	—	—	—
Gemma 3 270M New	Google Gemma3	✓	✓	✓	✓	✓	✓	✓	—	—
Gemma 4 E2B New	Google Gemma4	✓	✓	✓	✓	✓	✓	—	✓	—
GPT OSS 20B New	OpenAI GPT OSS	✓	✓	✓	—	—	✓	—	—	—
Llama 3.2 3B New	Meta Llama 3	✓	✓	✓	✓	✓	✓	✓	—	—
MiniMax M2.7 New	MiniMax M2.7	✓	—	—	—	—	—	—	✓	—
Ministral 3 3B Instruct New	Mistral AI Ministral 3	✓	✓	✓	✓	✓	✓	✓	—	—
Nemotron3 Nano 30B-A3B New	NVIDIA Nemotron	✓	✓	✓	✓	✓	✓	✓	—	—
Qwen3 4B New	Alibaba Qwen3	✓	✓	✓	✓	✓	✓	—	—	—
Qwen3.5 35B-A3B (MoE) New	Alibaba Qwen3.5	✓	✓	✓	—	—	✓	—	—	—
Qwen3.6 35B-A3B (MoE) New	Alibaba Qwen3.6	✓	✓	✓	—	—	✓	—	—	—
Gemma 3 1B New	Google Gemma3	✓	✓	✓	✓	✓	✓	✓	—	—
Gemma 4 12B New	Google Gemma4	✓	✓	✓	—	—	✓	—	✓	—
Gemma 4 E4B New	Google Gemma4	✓	✓	✓	✓	✓	✓	—	✓	—
GPT OSS 120B New	OpenAI GPT OSS	✓	✓	—	—	—	✓	—	—	—
Llama 3.1 8B New	Meta Llama 3	✓	✓	✓	✓	✓	✓	✓	—	—
Ministral 3 8B Instruct New	Mistral AI Ministral 3	✓	✓	✓	✓	✓	✓	✓	—	—
Nemotron Nano 9B v2 New	NVIDIA Nemotron	✓	✓	—	—	—	✓	—	—	—
Qwen3.5 27B New	Alibaba Qwen3.5	✓	✓	✓	—	—	✓	—	—	—
Qwen3.6 27B New	Alibaba Qwen3.6	✓	✓	✓	—	—	✓	—	—	—
Qwen3 8B New	Alibaba Qwen3	✓	✓	✓	✓	—	✓	—	—	—
Cosmos Reason 2 2B New	NVIDIA Cosmos	✓	✓	✓	✓	✓	✓	—	✓	—
Gemma 3 4B New	Google Gemma3	✓	✓	✓	✓	✓	✓	✓	—	—
Gemma 4 26B-A4B New	Google Gemma4	✓	✓	✓	—	—	✓	—	✓	—
Llama 3.1 70B New	Meta Llama 3	✓	✓	✓	✓	✓	✓	✓	—	—
Ministral 3 14B Instruct New	Mistral AI Ministral 3	✓	✓	✓	✓	✓	✓	✓	—	—
Nemotron 3 Super 120B-A12B New	NVIDIA Nemotron	✓	—	—	—	—	✓	—	✓	—
Nemotron Nano 12B VL New	NVIDIA Nemotron	✓	✓	—	—	—	✓	—	—	—
Qwen3 30B-A3B (MoE) New	Alibaba Qwen3	✓	✓	✓	—	—	✓	—	—	—
Qwen3.5 9B New	Alibaba Qwen3.5	✓	✓	✓	✓	—	✓	—	—	—
Cosmos3 Edge New	NVIDIA Cosmos	✓	✓	✓	—	—	✓	—	—	—
Cosmos Reason 2 8B New	NVIDIA Cosmos	✓	✓	✓	✓	✓	✓	—	✓	—
Gemma 3 12B New	Google Gemma3	✓	✓	✓	✓	✓	✓	✓	—	—
Gemma 4 31B New	Google Gemma4	✓	✓	✓	—	—	✓	—	✓	—
Ministral 3 3B Reasoning New	Mistral AI Ministral 3	✓	✓	✓	✓	✓	✓	—	—	—
Qwen3 32B New	Alibaba Qwen3	✓	✓	—	—	—	✓	—	—	—
Nemotron 3 Nano Omni New	NVIDIA Nemotron	✓	✓	✓	—	—	✓	✓	✓	—
Qwen3.5 4B New	Alibaba Qwen3.5	✓	✓	✓	✓	✓	✓	—	—	—
DiffusionGemma 26B-A4B New	Google Gemma4	✓	✓	✓	—	—	✓	—	—	—
Cosmos3 Nano New	NVIDIA Cosmos	✓	✓	—	—	—	✓	—	—	—
Gemma 3 27B New	Google Gemma3	✓	✓	✓	✓	✓	✓	✓	—	—
Ministral 3 8B Reasoning New	Mistral AI Ministral 3	✓	✓	✓	✓	—	✓	—	—	—
Qwen3.5 0.8B New	Alibaba Qwen3.5	✓	✓	✓	✓	✓	✓	—	—	—
Qwen3 VL 4B New	Alibaba Qwen3	✓	✓	✓	✓	✓	✓	—	—	—
Ministral 3 14B Reasoning New	Mistral AI Ministral 3	✓	✓	✓	—	—	✓	—	—	—
Qwen3 VL 8B New	Alibaba Qwen3	✓	✓	✓	✓	—	✓	—	—	—

Featured Models

Nemotron 3.5 Bolt E4B 4GB

d1-3B

Qwen3.8 Flash Next

All Models

Liquid AI d1

FLUX.3 Action

Qwen 3.8

NVIDIA Nemotron

Meta Muse Glimmer

Qwen 3.6

Gemma 4

NVIDIA Cosmos

Qwen 3.5

OpenAI GPT OSS

Qwen 3

Ministral 3

Llama 3

Gemma 3

MiniMax M2.7

No models found

Performance on Jetson