llamaperf

NVIDIA Jetson AGX Thor 128GB vs NVIDIA RTX Pro 6000 Blackwell for local LLMs

8 reports on the NVIDIA Jetson AGX Thor 128GB and 81 on the NVIDIA RTX Pro 6000 Blackwell

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 NVIDIA RTX Pro 6000 Blackwell has 105.5 generation tokens/s (6 runs); prompt processing 5110.0 tokens/s (6 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 6.6x higher on the NVIDIA RTX Pro 6000 Blackwell (273 GB/s on the NVIDIA Jetson AGX Thor 128GB, 1,792 on the NVIDIA RTX Pro 6000 Blackwell). Across 2 shared models with generation measurements on both cards, the NVIDIA Jetson AGX Thor 128GB's median is higher on 0 and the NVIDIA RTX Pro 6000 Blackwell's on 2.

NVIDIA Jetson AGX Thor 128GB
Memory
128GB unified
Memory bandwidth
273 GB/s
FP16 compute
258.8 TFLOPS
Reports
8
NVIDIA RTX Pro 6000 Blackwell
Memory
96GB
Memory bandwidth
1,792 GB/s
FP16 compute
503 TFLOPS
Reports
81

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

ModelNVIDIA Jetson AGX Thor 128GBNVIDIA RTX Pro 6000 Blackwell
Qwen3.8 125B · 6B active4-bit36.7one runPP 899.0 (one run)engine not stated256K context105.56 runsPP 5110.0 (6 runs)llama.cpp, ik_llama.cpp +2, 3 not stated512 to 256K context, 1 not stated
Qwen3.8 27B4-bit12.0one runengine not statedcontext not stated67.0one runengine not statedcontext 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.

ModelNVIDIA Jetson AGX Thor 128GBNVIDIA RTX Pro 6000 Blackwell
Qwen3.8 125B · 6B active10.0 t/sQ6_K83.1 t/sQ5_K_S
Qwen3.8 27B2.8 t/sFP1618.3 t/sFP16
Qwen3.6 35B · 3B active10.0 t/sFP1657.5 t/sFP16
DeepSeek V4 Flash 284B · 13B active26.5 t/sQ2_K130.8 t/sQ2_K
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B2.8 t/sFP1618.3 t/sFP16
Gemma 4 26B · 4B active7.5 t/sFP1649.3 t/sFP16
GLM-5.3 320B · 18B active8.8 t/sQ2_K6.8 t/sQ2_K, experts in RAM

Change the context, RAM or model in the calculator: NVIDIA Jetson AGX Thor 128GB · NVIDIA RTX Pro 6000 Blackwell

Every report on each card, with its source: NVIDIA Jetson AGX Thor 128GB · NVIDIA RTX Pro 6000 Blackwell

More comparisons