NVIDIA H200 vs NVIDIA Jetson AGX Thor 128GB for local LLMs
2 reports on the NVIDIA H200 and 4 on the NVIDIA Jetson AGX Thor 128GB
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 17.6x higher on the NVIDIA H200 (4,800 GB/s on the NVIDIA H200, 273 on the NVIDIA Jetson AGX Thor 128GB). The estimates below compare them on the models people run most.
- Memory
- 141GB
- Memory bandwidth
- 4,800 GB/s
- FP16 compute
- 989 TFLOPS
- Reports
- 2
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 258.8 TFLOPS
- Reports
- 4
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 H200 | NVIDIA Jetson AGX Thor 128GB |
|---|---|---|
| Qwen3.8 27B | 48.9 t/sFP16 | 2.8 t/sFP16 |
| Qwen3.8 125B · 6B active | 191.1 t/sQ6_K | 10.0 t/sQ6_K |
| DeepSeek V4 Flash 284B · 13B active | 362.5 t/sQ3_K_S | 26.5 t/sQ2_K |
| Qwen3.6 35B · 3B active | 176.0 t/sFP16 | 10.0 t/sFP16 |
| Qwen3.6 27B | 48.9 t/sFP16 | 2.8 t/sFP16 |
| Gemma 4 26B · 4B active | 132.0 t/sFP16 | 7.5 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA H200 · NVIDIA Jetson AGX Thor 128GB
Every report on each card, with its source: NVIDIA H200 · NVIDIA Jetson AGX Thor 128GB