on

Can the NVIDIA Jetson AGX Orin 64GB (64 GB) run Phi-3 Vision 128K Instruct?

33Basic quality (D) · 33 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q6_K it needs about 11.8 GB of 57.6 GB usable, with an estimated speed of 42.0 tok/s.

Best quant
Q6_K
Generation speed
42.0 tok/s
Prompt processing
920 tok/s
First token (1K prompt)
1.1 s
Largest safe context
121K

Best app to run it on the NVIDIA Jetson AGX Orin 64GB (64 GB)

On Linux on ARM boards

vLLM

Inference server · runs on vLLM

  • The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
vllm serve microsoft/Phi-3-vision-128k-instruct
  • SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
  • Docker Model Runner Handy if you already work in Docker.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Phi-3 Vision 128K Instruct

Original weights · Hugging Face

Full-precision files from Microsoft, for fine-tuning, vLLM, Transformers.

huggingface.co/microsoft/Phi-3-vision-128k-instruct (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 33Basic quality (D) · 33 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q6_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great
How well it runs on the NVIDIA Jetson AGX Orin 64GB (64 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.15.1 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.4.7 / 15
Match score59.9 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA Jetson AGX Orin 64GB (64 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 10.1 GB 57.6 GB 99.5 tok/s Runs great 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 10.5 GB 57.6 GB 78.3 tok/s Runs great 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 11.0 GB 57.6 GB 60.6 tok/s Runs great 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q5_K_M 11.4 GB 57.6 GB 50.0 tok/s Runs great 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 11.8 GB 57.6 GB 42.0 tok/s Runs great 33Basic quality (D) · 33 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 12.8 GB 57.6 GB 30.8 tok/s Runs great 34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 16.7 GB 57.6 GB 14.2 tok/s Runs well 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does Phi-3 Vision 128K Instruct need on the NVIDIA Jetson AGX Orin 64GB 64GB?

At Q6_K it needs about 11.8 GB. The NVIDIA Jetson AGX Orin 64GB 64GB has 57.6 GB usable.

How fast is Phi-3 Vision 128K Instruct on the NVIDIA Jetson AGX Orin 64GB 64GB?

About 42.0 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Phi-3 Vision 128K Instruct should I use on the NVIDIA Jetson AGX Orin 64GB 64GB?

Q6_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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?