NVIDIA RTX 5090 vs NVIDIA RTX Pro 6000 Blackwell for local LLMs
169 reports on the NVIDIA RTX 5090 and 70 on the NVIDIA RTX Pro 6000 Blackwell
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the NVIDIA RTX 5090 has 80.0 generation tokens/s (7 runs); the NVIDIA RTX Pro 6000 Blackwell has 67.0 generation 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 5090, 1,792 on the NVIDIA RTX Pro 6000 Blackwell). Across 2 shared models with generation measurements on both cards, the NVIDIA RTX 5090's median is higher on 2 and the NVIDIA RTX Pro 6000 Blackwell's on 0.
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 169
- Memory
- 96GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 503 TFLOPS
- Reports
- 70
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 5090 | NVIDIA RTX Pro 6000 Blackwell |
|---|---|---|
| Qwen3.8 27B4-bit | 80.07 runsllama.cpp, TensorSharp +1, 2 not stated40K to 256K context, 2 not stated | 67.0one runengine not statedcontext not stated |
| Gemma 4 31B4-bit | 64.0one runOllama32K context | 51.0one runPP 15359.0 (one run)vLLM16K context |
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 5090 | NVIDIA RTX Pro 6000 Blackwell |
|---|---|---|
| Qwen3.8 27B | 44.9 t/sQ6_K | 18.3 t/sFP16 |
| Gemma 4 31B | 46.2 t/sQ5_K_M | 15.9 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 |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: NVIDIA RTX 5090 · NVIDIA RTX Pro 6000 Blackwell
Every report on each card, with its source: NVIDIA RTX 5090 · NVIDIA RTX Pro 6000 Blackwell