NVIDIA RTX 5090 Laptop 24GB vs NVIDIA RTX Pro 6000 Blackwell for local LLMs
4 reports on the NVIDIA RTX 5090 Laptop 24GB and 51 on the NVIDIA RTX Pro 6000 Blackwell
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the NVIDIA RTX 5090 Laptop 24GB runs at 30.0 tokens per second (one run) and the NVIDIA RTX Pro 6000 Blackwell at 67.0 (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 2.0x higher on the NVIDIA RTX Pro 6000 Blackwell (896 GB/s on the NVIDIA RTX 5090 Laptop 24GB, 1,792 on the NVIDIA RTX Pro 6000 Blackwell).
- Memory
- 24GB
- Memory bandwidth
- 896 GB/s
- FP16 compute
- 200 TFLOPS
- Reports
- 4
- Memory
- 96GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 503 TFLOPS
- Reports
- 51
Measured on both
Median tokens per second 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 quant level. Engines and context lengths can still differ between the runs. How to read these
| Model | NVIDIA RTX 5090 Laptop 24GB | NVIDIA RTX Pro 6000 Blackwell |
|---|---|---|
| Qwen3.8 27B4-bit | 30.0one run | 67.0one run |
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 Laptop 24GB | NVIDIA RTX Pro 6000 Blackwell |
|---|---|---|
| Qwen3.8 27B | 32.4 t/sQ4_K_M | 18.3 t/sFP16 |
| Qwen3.8 125B · 6B active | 19.4 t/sQ2_K, experts in RAM | 83.1 t/sQ5_K_S |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 130.8 t/sQ2_K |
| Qwen3.6 35B · 3B active | 115.0 t/sQ4_K_S | 57.5 t/sFP16 |
| Qwen3.6 27B | 32.4 t/sQ4_K_M | 18.3 t/sFP16 |
| Gemma 4 26B · 4B active | 73.2 t/sQ5_K_S | 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 Laptop 24GB · NVIDIA RTX Pro 6000 Blackwell
Every report on each card, with its source: NVIDIA RTX 5090 Laptop 24GB · NVIDIA RTX Pro 6000 Blackwell