NVIDIA CMP 170HX 64GB (unlocked) vs NVIDIA Jetson AGX Thor 128GB for local LLMs
11 reports on the NVIDIA CMP 170HX 64GB (unlocked) 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 5.5x higher on the NVIDIA CMP 170HX 64GB (unlocked) (1,493 GB/s on the NVIDIA CMP 170HX 64GB (unlocked), 273 on the NVIDIA Jetson AGX Thor 128GB). The estimates below compare them on the models people run most.
- Memory
- 64GB
- Memory bandwidth
- 1,493 GB/s
- FP16 compute
- not on record
- Reports
- 11
- 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 CMP 170HX 64GB (unlocked) | NVIDIA Jetson AGX Thor 128GB |
|---|---|---|
| Qwen3.8 27B | 30.4 t/sQ8_0 | 2.8 t/sFP16 |
| Qwen3.8 125B · 6B active | 127.0 t/sQ3_K_S | 10.0 t/sQ6_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 26.5 t/sQ2_K |
| Qwen3.6 35B · 3B active | 109.5 t/sQ8_0 | 10.0 t/sFP16 |
| Qwen3.6 27B | 30.4 t/sQ8_0 | 2.8 t/sFP16 |
| Gemma 4 26B · 4B active | 82.1 t/sQ8_0 | 7.5 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA CMP 170HX 64GB (unlocked) · NVIDIA Jetson AGX Thor 128GB
Every report on each card, with its source: NVIDIA CMP 170HX 64GB (unlocked) · NVIDIA Jetson AGX Thor 128GB
More comparisons
- NVIDIA CMP 170HX 64GB (unlocked) vs NVIDIA RTX 3090
- NVIDIA Jetson AGX Thor 128GB vs NVIDIA RTX 3090
- NVIDIA CMP 170HX 64GB (unlocked) vs NVIDIA RTX 5090
- NVIDIA Jetson AGX Thor 128GB vs NVIDIA RTX 5090
- NVIDIA CMP 170HX 64GB (unlocked) vs AMD Strix Halo 128GB
- NVIDIA Jetson AGX Thor 128GB vs AMD Strix Halo 128GB