NVIDIA RTX Pro 6000 Blackwell vs NVIDIA RTX PRO 6000 Max-Q for local LLMs
70 reports on the NVIDIA RTX Pro 6000 Blackwell and 13 on the NVIDIA RTX PRO 6000 Max-Q
Which is faster for local LLMs?
On DeepSeek V4 Flash 284B · 13B active at 2-bit, the NVIDIA RTX Pro 6000 Blackwell has 45.9 generation tokens/s (one run); prompt processing 362.3 tokens/s (one run); the NVIDIA RTX PRO 6000 Max-Q has 43.6 generation tokens/s (one run); prompt processing 262.0 tokens/s (one run). 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 about the same on both (1,792 GB/s on the NVIDIA RTX Pro 6000 Blackwell, 1,792 on the NVIDIA RTX PRO 6000 Max-Q).
- Memory
- 96GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 503 TFLOPS
- Reports
- 70
- Memory
- 96GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 439 TFLOPS
- Reports
- 13
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 RTX Pro 6000 Blackwell | NVIDIA RTX PRO 6000 Max-Q |
|---|---|---|
| DeepSeek V4 Flash 284B · 13B active2-bit | 45.9one runPP 362.3 (one run)ds42K context | 43.6one runPP 262.0 (one run)engine 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.
| Model | NVIDIA RTX Pro 6000 Blackwell | NVIDIA RTX PRO 6000 Max-Q |
|---|---|---|
| DeepSeek V4 Flash 284B · 13B active | 130.8 t/sQ2_K | 130.8 t/sQ2_K |
| Qwen3.8 27B | 18.3 t/sFP16 | 18.3 t/sFP16 |
| Qwen3.8 125B · 6B active | 83.1 t/sQ5_K_S | 83.1 t/sQ5_K_S |
| Qwen3.6 35B · 3B active | 57.5 t/sFP16 | 57.5 t/sFP16 |
| Qwen3.6 27B | 18.3 t/sFP16 | 18.3 t/sFP16 |
| Gemma 4 26B · 4B active | 49.3 t/sFP16 | 49.3 t/sFP16 |
| GLM-5.3 320B · 18B active | 6.8 t/sQ2_K, experts in RAM | 6.8 t/sQ2_K, experts in RAM |
Change the context, RAM or model in the calculator: NVIDIA RTX Pro 6000 Blackwell · NVIDIA RTX PRO 6000 Max-Q
Every report on each card, with its source: NVIDIA RTX Pro 6000 Blackwell · NVIDIA RTX PRO 6000 Max-Q