What can the Jetson AGX Orin run?
With 64 GB, 9 of 12 popular open models fit. The best pick is Qwen3 30B-A3B at about 36 tok/s, faster than you can read.
ollama run qwen3:30bFirst time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.
Every model the Jetson AGX Orin 32 GB can run
8 of 12 fit. Best pick: Qwen3 30B-A3B.
- Qwen3 4BQuick everyday chat and summaries~45 tok/sRuns great
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~22 tok/sUsable
qwen3:8b - Gemma 3 12BReads images as well as text~14 tok/sUsable
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~12 tok/sUsable
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoning~36 tok/sRuns great
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its size~7 tok/sSlow
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speed~36 tok/sRuns great
qwen3:30b - Qwen3 32BStrong coding and long answers~6 tok/sSlow
qwen3:32b - Llama 3.3 70BClose to the big cloud modelsneeds 45 GBToo big
llama3.3:70b - gpt-oss 120BOpenAI's largest open modelneeds 67 GBToo big
gpt-oss:120b - Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigsneeds 144 GBToo big
qwen3:235b - DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigsneeds 406 GBToo big
deepseek-r1:671b
Every model the Jetson AGX Orin 64 GB can run
9 of 12 fit. Best pick: Qwen3 30B-A3B.
- Qwen3 4BQuick everyday chat and summaries~45 tok/sRuns great
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~22 tok/sUsable
qwen3:8b - Gemma 3 12BReads images as well as text~14 tok/sUsable
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~12 tok/sUsable
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoning~36 tok/sRuns great
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its size~7 tok/sSlow
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speed~36 tok/sRuns great
qwen3:30b - Qwen3 32BStrong coding and long answers~6 tok/sSlow
qwen3:32b - Llama 3.3 70BClose to the big cloud models~3 tok/sSlow
llama3.3:70b - gpt-oss 120BOpenAI's largest open modelneeds 67 GBToo big
gpt-oss:120b - Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigsneeds 144 GBToo big
qwen3:235b - DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigsneeds 406 GBToo big
deepseek-r1:671b
Can the Jetson AGX Orin run it?
Can the Jetson AGX Orin run Qwen3 32B?
Yes. Qwen3 32B needs about 22 GB and the Jetson AGX Orin with 32 GB of unified memory leaves about 24 GB for models. Expect about 6 tok/s, slow, but it works.
Can the Jetson AGX Orin run Llama 3.3 70B?
Yes, with 64 GB or more. Llama 3.3 70B needs about 45 GB and the Jetson AGX Orin with 64 GB of unified memory leaves about 48 GB for models. Expect about 3 tok/s, slow, but it works. The 32 GB version doesn't have room.
Can the Jetson AGX Orin run gpt-oss 120B?
No. gpt-oss 120B needs about 67 GB and the Jetson AGX Orin has at most 64 GB of unified memory, of which about 48 GB is usable for models. The most capable model it runs well is Qwen3 30B-A3B, at about 36 tok/s.
Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (205 GB/s) divided by the active weight size, with efficiency calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. The GPU shares memory with the system, so we count about three quarters of it for models. Real results are usually within about a third. Measured one yourself? Send us the number.
The Ryzen AI Max+ 395 mini PC, 128 GB runs gpt-oss 120B at about 31 tok/s, from $3,400 used.