NVIDIA RTX 5090 vs NVIDIA RTX PRO 6000 Max-Q for local LLMs
161 reports on the NVIDIA RTX 5090 and 13 on the NVIDIA RTX PRO 6000 Max-Q
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 about the same on both (1,792 GB/s on the NVIDIA RTX 5090, 1,792 on the NVIDIA RTX PRO 6000 Max-Q). The estimates below compare them on the models people run most.
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 161
- Memory
- 96GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 439 TFLOPS
- Reports
- 13
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 RTX 5090 | NVIDIA RTX PRO 6000 Max-Q |
|---|---|---|
| Qwen3.8 27B | 44.9 t/sQ6_K | 18.3 t/sFP16 |
| Qwen3.8 125B · 6B active | 20.3 t/sQ2_K, experts in RAM | 83.1 t/sQ5_K_S |
| Qwen3.6 35B · 3B active | 163.0 t/sQ5_K_M | 57.5 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 130.8 t/sQ2_K |
| Qwen3.6 27B | 44.9 t/sQ6_K | 18.3 t/sFP16 |
| Gemma 4 26B · 4B active | 114.5 t/sQ6_K | 49.3 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA RTX 5090 · NVIDIA RTX PRO 6000 Max-Q
Every report on each card, with its source: NVIDIA RTX 5090 · NVIDIA RTX PRO 6000 Max-Q