NVIDIA Jetson AGX Thor 128GB vs NVIDIA RTX Pro 5000 Blackwell 72GB for local LLMs
8 reports on the NVIDIA Jetson AGX Thor 128GB and 6 on the NVIDIA RTX Pro 5000 Blackwell 72GB
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 4.9x higher on the NVIDIA RTX Pro 5000 Blackwell 72GB (273 GB/s on the NVIDIA Jetson AGX Thor 128GB, 1,344 on the NVIDIA RTX Pro 5000 Blackwell 72GB). 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
- 8
- Memory
- 72GB
- Memory bandwidth
- 1,344 GB/s
- FP16 compute
- 258 TFLOPS
- Reports
- 6
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 Pro 5000 Blackwell 72GB |
|---|---|---|
| Qwen3.8 27B | 2.8 t/sFP16 | 13.7 t/sFP16 |
| Qwen3.8 125B · 6B active | 10.0 t/sQ6_K | 95.0 t/sQ3_K_M |
| Qwen3.6 35B · 3B active | 10.0 t/sFP16 | 98.6 t/sQ8_0 |
| DeepSeek V4 Flash 284B · 13B active | 26.5 t/sQ2_K | 9.2 t/sQ2_K, experts in RAM |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 2.8 t/sFP16 | 13.7 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA Jetson AGX Thor 128GB · NVIDIA RTX Pro 5000 Blackwell 72GB
Every report on each card, with its source: NVIDIA Jetson AGX Thor 128GB · NVIDIA RTX Pro 5000 Blackwell 72GB
More comparisons
- NVIDIA RTX Pro 5000 Blackwell 72GB vs AMD Strix Halo 128GB
- NVIDIA Jetson AGX Thor 128GB vs AMD Strix Halo 128GB
- NVIDIA RTX 3090 vs NVIDIA RTX Pro 5000 Blackwell 72GB
- NVIDIA Jetson AGX Thor 128GB vs NVIDIA RTX 3090
- NVIDIA RTX 5090 vs NVIDIA RTX Pro 5000 Blackwell 72GB
- NVIDIA Jetson AGX Thor 128GB vs NVIDIA RTX 5090