Home › Model Memory Fit
Model Memory Fit

Does this model fit in this Jetson's memory?

Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026

22 LLM, VLM and ASR models across 7 Jetson modules. Weights come from a published quantised artefact size when one exists, else parameters × bytes-per-parameter; KV cache from the model's own architecture; runtime overhead, OS headroom and reserve from the memory budget shared with Camera Stream Capacity. Every number traces to a source. Download the whole registry as JSON with provenance, or read the methodology.

Models × modules at a glance

Verdict and total memory at Q4 quantisation, 4096-token context, 1 sequence, llama.cpp, headless. FITS is under 85% of module memory, TIGHT is 85–100%, DOES NOT FIT is at or over capacity. Click a cell for the full breakdown; click a model name for its facts and every quantisation.

ModelOrin Nano 8GBOrin NX 8GBOrin NX 16GBAGX Orin 32GBAGX Orin 64GBThor T5000T4000
Llama 3.2 1B Instruct
LLM · 1.24 B
FITS
2.4 GB
FITS
2.4 GB
FITS
2.4 GB
FITS
2.4 GB
FITS
2.4 GB
FITS
2.4 GB
FITS
2.4 GB
Llama 3.2 3B Instruct
LLM · 3.21 B
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
Llama 3.1 8B Instruct
LLM · 8.03 B
TIGHT
7.3 GB
TIGHT
7.3 GB
FITS
7.3 GB
FITS
7.3 GB
FITS
7.3 GB
FITS
7.3 GB
FITS
7.3 GB
Qwen2.5 1.5B Instruct
LLM · 1.54 B
FITS
2.6 GB
FITS
2.6 GB
FITS
2.6 GB
FITS
2.6 GB
FITS
2.6 GB
FITS
2.6 GB
FITS
2.6 GB
Qwen2.5 3B Instruct
LLM · 3.09 B
FITS
3.6 GB
FITS
3.6 GB
FITS
3.6 GB
FITS
3.6 GB
FITS
3.6 GB
FITS
3.6 GB
FITS
3.6 GB
Qwen2.5 7B Instruct
LLM · 7.61 B
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
Qwen2.5-VL 3B Instruct
VLM · 3.76 B
FITS
4.6 GB
FITS
4.6 GB
FITS
4.6 GB
FITS
4.6 GB
FITS
4.6 GB
FITS
4.6 GB
FITS
4.6 GB
Qwen2.5-VL 7B Instruct
VLM · 8.29 B
TIGHT
7.7 GB
TIGHT
7.7 GB
FITS
7.7 GB
FITS
7.7 GB
FITS
7.7 GB
FITS
7.7 GB
FITS
7.7 GB
Phi-3.5-mini Instruct
LLM · 3.8 B
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
Phi-4-mini Instruct
LLM · 3.8 B
FITS
4.7 GB
FITS
4.7 GB
FITS
4.7 GB
FITS
4.7 GB
FITS
4.7 GB
FITS
4.7 GB
FITS
4.7 GB
Gemma 2 2B IT
LLM · 2.61 B
FITS
3.7 GB
FITS
3.7 GB
FITS
3.7 GB
FITS
3.7 GB
FITS
3.7 GB
FITS
3.7 GB
FITS
3.7 GB
Gemma 3 4B IT
VLM · 4.3 B
FITS
5.7 GB
FITS
5.7 GB
FITS
5.7 GB
FITS
5.7 GB
FITS
5.7 GB
FITS
5.7 GB
FITS
5.7 GB
SmolVLM 256M Instruct
VLM · 0.26 B
FITS
1.7 GB
FITS
1.7 GB
FITS
1.7 GB
FITS
1.7 GB
FITS
1.7 GB
FITS
1.7 GB
FITS
1.7 GB
SmolVLM 500M Instruct
VLM · 0.51 B
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
SmolVLM 2.2B Instruct
VLM · 2.25 B
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
FITS
4.1 GB
LLaVA 1.5 7B
VLM · 7.06 B
DOES NOT FIT
9.0 GB
DOES NOT FIT
9.0 GB
FITS
9.0 GB
FITS
9.0 GB
FITS
9.0 GB
FITS
9.0 GB
FITS
9.0 GB
VILA 1.5 3B
VLM · 3.15 B
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
FITS
5.6 GB
VILA 1.5 8B (Llama-3)
VLM · 8.49 B
DOES NOT FIT
8.4 GB
DOES NOT FIT
8.4 GB
FITS
8.4 GB
FITS
8.4 GB
FITS
8.4 GB
FITS
8.4 GB
FITS
8.4 GB
Whisper small
ASR · 0.24 B
FITS
1.6 GB
FITS
1.6 GB
FITS
1.6 GB
FITS
1.6 GB
FITS
1.6 GB
FITS
1.6 GB
FITS
1.6 GB
Whisper medium
ASR · 0.77 B
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
FITS
2.0 GB
Whisper large-v3
ASR · 1.55 B
FITS
2.5 GB
FITS
2.5 GB
FITS
2.5 GB
FITS
2.5 GB
FITS
2.5 GB
FITS
2.5 GB
FITS
2.5 GB
Mistral 7B Instruct v0.3
LLM · 7.25 B
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB
FITS
6.7 GB

Module memory

Installed memory per module, from the NVIDIA technical specifications table (class A). Jetson modules share one memory pool between CPU and GPU: OS, runtime and model weights all draw on it.

ModuleMemorySource
Jetson Orin Nano 8GB8 GBNVIDIA · nvidia.com:jetson-modules-spec-table · verified 2026-09-07
Jetson Orin NX 8GB8 GBNVIDIA · nvidia.com:jetson-modules-spec-table · verified 2026-09-07
Jetson Orin NX 16GB16 GBNVIDIA · nvidia.com:jetson-modules-spec-table · verified 2026-09-07
Jetson AGX Orin 32GB32 GBNVIDIA · nvidia.com:jetson-modules-spec-table · verified 2026-09-07
Jetson AGX Orin 64GB64 GBNVIDIA · nvidia.com:jetson-modules-spec-table · verified 2026-09-07
Jetson Thor T5000128 GBNVIDIA · nvidia.com:jetson-modules-spec-table · verified 2026-09-07
Jetson T400064 GBNVIDIA · nvidia.com:jetson-modules-spec-table · verified 2026-09-07

Method and data

Check your exact combination.

Pick the model, module, quantisation, context length and concurrency — the engine builds the breakdown live and gives you a permanent link.

OPEN MODEL MEMORY FIT →