NVIDIA Jetson AGX Thor 128GB vs AMD Strix Halo 128GB for local LLMs
8 reports on the NVIDIA Jetson AGX Thor 128GB and 348 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Qwen3.8 125B · 6B active at 4-bit, the NVIDIA Jetson AGX Thor 128GB has 36.7 generation tokens/s (one run); prompt processing 899.0 tokens/s (one run); the AMD Strix Halo 128GB has 26.6 generation tokens/s (8 runs); prompt processing 1700.5 tokens/s (7 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 7% higher on the NVIDIA Jetson AGX Thor 128GB (273 GB/s on the NVIDIA Jetson AGX Thor 128GB, 256 on the AMD Strix Halo 128GB). Across 2 shared models with generation measurements on both cards, the NVIDIA Jetson AGX Thor 128GB's median is higher on 1 and the AMD Strix Halo 128GB's on 1.
- Memory
- 128GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 258.8 TFLOPS
- Reports
- 8
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 348
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
| Model | NVIDIA Jetson AGX Thor 128GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active4-bit | 36.7one runPP 899.0 (one run)engine not stated256K context | 26.68 runsPP 1700.5 (7 runs)Gufo, llama.cpp, 1 not stated16K to 160K context, 3 not stated |
| Qwen3.8 27B4-bit | 12.0one runengine not statedcontext not stated | 13.14 runsPP 378.2 (3 runs)llama.cpp, 1 not stated32K context, 3 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.
| Model | NVIDIA Jetson AGX Thor 128GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 125B · 6B active | 10.0 t/sQ6_K | 12.6 t/sQ6_K |
| Qwen3.8 27B | 2.8 t/sFP16 | 3.5 t/sFP16 |
| Qwen3.6 35B · 3B active | 10.0 t/sFP16 | 12.6 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 26.5 t/sQ2_K | 33.5 t/sQ2_K |
| 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 | 3.5 t/sFP16 |
| Gemma 4 26B · 4B active | 7.5 t/sFP16 | 9.5 t/sFP16 |
| GLM-5.3 320B · 18B active | 8.8 t/sQ2_K | 11.1 t/sQ2_K |
Change the context, RAM or model in the calculator: NVIDIA Jetson AGX Thor 128GB · AMD Strix Halo 128GB
Every report on each card, with its source: NVIDIA Jetson AGX Thor 128GB · AMD Strix Halo 128GB