NVIDIA Jetson AGX Thor 128GB vs NVIDIA RTX 5090 for local LLMs
4 reports on the NVIDIA Jetson AGX Thor 128GB and 114 on the NVIDIA RTX 5090
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 6.6x higher on the NVIDIA RTX 5090 (273 GB/s on the NVIDIA Jetson AGX Thor 128GB, 1,792 on the NVIDIA RTX 5090). The estimates below compare them on the models people run most.
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 258.8 TFLOPS
- Reports
- 4
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 114
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.
| Model | NVIDIA Jetson AGX Thor 128GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.8 27B | 2.8 t/sFP16 | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | 10.0 t/sQ6_K | 20.3 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | 26.5 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 10.0 t/sFP16 | 163.0 t/sQ5_K_M |
| Qwen3.6 27B | 2.8 t/sFP16 | 44.9 t/sQ6_K |
| Gemma 4 26B · 4B active | 7.5 t/sFP16 | 114.5 t/sQ6_K |
Change the context, RAM or model in the calculator: NVIDIA Jetson AGX Thor 128GB · NVIDIA RTX 5090
Every report on each card, with its source: NVIDIA Jetson AGX Thor 128GB · NVIDIA RTX 5090