NVIDIA Jetson Orin NX 16GB

Hardware · NVIDIA

What AI models can the NVIDIA Jetson Orin NX 16GB (16 GB) run?

Unified memory
16.0 GB
Usable for models
13.6 GB
Memory bandwidth
102 GB/s
Runs models on
GPU (CUDA)
Released
2023
397 / 622 LLMs run Best: Mellum2.1 Thinking (12B-A2.5B) 54 / 61 Image models run Best: FLUX.2 [klein] 4B 15 / 43 Video models run Best: LTX-Video 2B 65 / 70 Decision models run Best: Jina Reranker v3.5

Models run on the GPU (CUDA) here, sharing the board’s memory with the system. We plan around 13.6 GB of the 16.0 GB (what Linux leaves free for a model). Ampere GPU with 1,024 CUDA cores and 32 Tensor Cores, plus two NVDLA v2 engines: 157 TOPS in Super mode (100 before JetPack 6.2).

More about this hardware

MakerNVIDIA
TypeSingle-board computer or edge AI board
GPU share of memory85% (what the GPU can typically be given for a model)
ChipNVIDIA Jetson Orin NX 16GB
AI acceleratorAmpere GPU with 1,024 CUDA cores and 32 Tensor Cores, plus two NVDLA v2 engines: 157 TOPS in Super mode (100 before JetPack 6.2).
Boards with this chipJetson Orin NX 16GB module · Carrier boards and boxes such as Seeed reComputer J4012
Memory type16 GB LPDDR5, 128-bit
Bandwidth figure102.4 GB/s, as the maker states it
Specificationswww.nvidia.com

Apps that run models well on the NVIDIA Jetson Orin NX 16GB (16 GB)

Linux on ARM boards

  1. OllamaOne command with Ollama’s own build of this model.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. llama.cppUsually the first to support new model architectures.
  4. Docker Model RunnerHandy if you already work in Docker.

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

Best LLMs for the NVIDIA Jetson Orin NX 16GB (16 GB)

Quality Model Quant Memory Speed Runs
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B)JetBrains Q4_K_M 9.2 GB 43.0 tok/s Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12BGoogle Q4_K_M 9.7 GB 10.5 tok/s Runs well
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle Q2_K 12.4 GB 46.4 tok/s Runs welltight fit
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7BInstitute of Foundation Models Q4_K_M 8.4 GB 14.0 tok/s Runs well
60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) Q8_0 10.3 GB 41.5 tok/s Runs great
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Raon-1 mini Preview (30B-A4B)KRAFTON Q2_K 13.3 GB 41.7 tok/s Runs welltight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. SenseNova Loop 9B PreviewSenseTime Q4_K_M 8.1 GB 13.0 tok/s Runs well
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. ERNIE 4.5 21B-A3B ThinkingBaidu Q3_K_M 12.9 GB 46.1 tok/s Runs welltight fit
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B)DeepGrove Q3_K_M 11.7 GB 80.6 tok/s Runs welltight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M 7.7 GB 13.4 tok/s Runs well
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Ornith 1.5 9BDeepReinforce Q4_K_M 7.8 GB 13.0 tok/s Runs well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 9BAlibaba Q4_K_M 7.8 GB 13.0 tok/s Runs well

Best Image models for the NVIDIA Jetson Orin NX 16GB (16 GB)

Quality Model Quant Memory Speed Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 4BBlack Forest Labs FP8 10.2 GB 9.1 s Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) FP8 12.6 GB 23 s Runs welltight fit
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs FP8 12.4 GB 52 s Slowtight fit
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu Q4 GGUF 11.3 GB 39 s Runs well
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs FP8 11.7 GB 17 s Runs welltight fit · encoder unloaded after use
54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. SDXL-Lightning (4-step)ByteDance FP16 8.9 GB 7.0 s Runs great

Best Video models for the NVIDIA Jetson Orin NX 16GB (16 GB)

Quality Model Quant Memory Speed Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 2BLightricks FP8 10.8 GB 3.8 min Runs great
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. CogVideoX 2BZhipu AI FP8 11.0 GB 9.1 min Runs well
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Bernini-R A14B (video generation + editing)ByteDance FP8 10.7 GB 2.4 h Very slowCPU offload
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Wan 2.1 T2V 1.3BAlibaba FP8 12.8 GB 36.2 min Slowtight fit
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. CogVideoX 5BZhipu AI FP8 9.6 GB 28.5 min Slowencoder unloaded after use

Best Decision models for the NVIDIA Jetson Orin NX 16GB (16 GB)

Quality Model Quant Memory Speed Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5Jina AI Q8_0 2.6 GB 126 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3Jina AI Q8_0 2.6 GB 126 ms Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. FRIDA-DecisionsSber AI F16 2.4 GB 100 ms Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. GLiNER2.5 DecideFastino F16 1.7 GB 61 ms Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 0.6BAlibaba Q8_0 2.6 GB 126 ms Runs great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 86MMeta F16 1.2 GB 69 ms Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-base v2Mixedbread Q8_0 2.2 GB 103 ms Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. GLiClass ModernBERT Large v3Knowledgator F16 1.5 GB 51 ms Runs great

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?