Granite 3.1 3B-A800M Instruct on NVIDIA Jetson Orin NX 16GB (16 GB)

Can the NVIDIA Jetson Orin NX 16GB (16 GB) run Granite 3.1 3B-A800M Instruct?

Yes, it runs great

Runs great. At Q8_0 it needs about 5.7 GB of 13.6 GB usable, with an estimated speed of 61.3 tok/s.

Best quant: Q8_0
Generation speed: 61.3 tok/s
Prompt processing: 3,420 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 125K

Best app to run it on the NVIDIA Jetson Orin NX 16GB (16 GB)

On Linux on ARM boards

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run granite3.1-moe:3b-instruct-q8_0

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

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 Granite 3.1 3B-A800M Instruct

Recommended for the NVIDIA Jetson Orin NX 16GB (16 GB): Q8_0. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run granite3.1-moe:3b-instruct-q8_0

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q8_0 file (opens in a new tab)

huggingface.co/bartowski/granite-3.1-3b-a800m-instruct-GGUF (opens in a new tab)

ollama run hf.co/bartowski/granite-3.1-3b-a800m-instruct-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/ibm-granite/granite-3.1-3b-a800m-instruct (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 20Basic quality (D) · 20 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.: How capable the model itself is at Q8_0, 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 Orin NX 16GB (16 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.	9.0 / 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.	9.7 / 15
Match score	58.7 / 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 Orin NX 16GB (16 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	3.5 GB	13.6 GB	143 tok/s	Runs great	14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	3.8 GB	13.6 GB	122 tok/s	Runs great	16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	4.2 GB	13.6 GB	103 tok/s	Runs great	19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	4.6 GB	13.6 GB	89.3 tok/s	Runs great	19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	4.9 GB	13.6 GB	78.2 tok/s	Runs great	19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	5.7 GB	13.6 GB	61.3 tok/s	Runs great	20Basic quality (D) · 20 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.	GGUF (opens in a new tab)
`F16`	8.8 GB	13.6 GB	31.7 tok/s	Runs great	20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) 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

20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 F16 · 81.0 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB F16 · 82.7 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 101 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q8_0 · 117 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) F16 · 61.8 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 106 tok/s · Runs great

Quick answers

How much memory does Granite 3.1 3B-A800M Instruct need on the NVIDIA Jetson Orin NX 16GB 16GB?

At Q8_0 it needs about 5.7 GB. The NVIDIA Jetson Orin NX 16GB 16GB has 13.6 GB usable.

How fast is Granite 3.1 3B-A800M Instruct on the NVIDIA Jetson Orin NX 16GB 16GB?

About 61.3 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Granite 3.1 3B-A800M Instruct should I use on the NVIDIA Jetson Orin NX 16GB 16GB?

Q8_0. 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.