llamaperf

NVIDIA Jetson AGX Thor 128GB vs NVIDIA RTX 3090 for local LLMs

8 reports on the NVIDIA Jetson AGX Thor 128GB and 271 on the NVIDIA RTX 3090

Which is faster for local LLMs?

On Qwen3.8 27B at 4-bit, the NVIDIA Jetson AGX Thor 128GB has 12.0 generation tokens/s (one run); the NVIDIA RTX 3090 has 38.4 generation tokens/s (7 runs); prompt processing 561.0 tokens/s (2 runs). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 3.4x higher on the NVIDIA RTX 3090 (273 GB/s on the NVIDIA Jetson AGX Thor 128GB, 936 on the NVIDIA RTX 3090).

NVIDIA Jetson AGX Thor 128GB
Memory
128GB unified
Memory bandwidth
273 GB/s
FP16 compute
258.8 TFLOPS
Reports
8
NVIDIA RTX 3090
Memory
24GB
Memory bandwidth
936 GB/s
FP16 compute
142 TFLOPS
Reports
271

Measured on both

Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these

ModelNVIDIA Jetson AGX Thor 128GBNVIDIA RTX 3090
Qwen3.8 27B4-bit12.0one runengine not statedcontext not stated38.47 runsPP 561.0 (2 runs)llama.cpp, vLLM +1, 1 not stated128K to 256K context, 2 not stated

Estimated by the calculator

The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape. Where a model was also measured above, the measurement wins.

ModelNVIDIA Jetson AGX Thor 128GBNVIDIA RTX 3090
Qwen3.8 27B2.8 t/sFP1633.9 t/sQ4_K_M
Qwen3.8 125B · 6B active10.0 t/sQ6_K19.4 t/sQ2_K, experts in RAM
Qwen3.6 35B · 3B active10.0 t/sFP16120.1 t/sQ4_K_S
DeepSeek V4 Flash 284B · 13B active26.5 t/sQ2_Kdoesn't fit at these settings
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B2.8 t/sFP1633.9 t/sQ4_K_M
Gemma 4 26B · 4B active7.5 t/sFP1676.4 t/sQ5_K_S

Change the context, RAM or model in the calculator: NVIDIA Jetson AGX Thor 128GB · NVIDIA RTX 3090

Every report on each card, with its source: NVIDIA Jetson AGX Thor 128GB · NVIDIA RTX 3090

More comparisons