NVIDIA B200 180GB vs NVIDIA Rubin 288GB for local LLMs
0 reports on the NVIDIA B200 180GB and 0 on the NVIDIA Rubin 288GB
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 2.8x higher on the NVIDIA Rubin 288GB (8,000 GB/s on the NVIDIA B200 180GB, 22,000 on the NVIDIA Rubin 288GB). The estimates below compare them on the models people run most.
- Memory
- 180GB
- Memory bandwidth
- 8,000 GB/s
- FP16 compute
- 2250 TFLOPS
- Reports
- 0
- Memory
- 288GB
- Memory bandwidth
- 22,000 GB/s
- FP16 compute
- 4000 TFLOPS
- Reports
- 0
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 B200 180GB | NVIDIA Rubin 288GB |
|---|---|---|
| Qwen3.8 27B | 81.5 t/sFP16 | 224.1 t/sFP16 |
| Qwen3.8 125B · 6B active | 266.2 t/sQ8_0 | 806.7 t/sQ8_0 |
| DeepSeek V4 Flash 284B · 13B active | 435.6 t/sQ4_K_S | 726.3 t/sQ6_K |
| Qwen3.6 35B · 3B active | 293.3 t/sFP16 | 806.7 t/sFP16 |
| Qwen3.6 27B | 81.5 t/sFP16 | 224.1 t/sFP16 |
| Gemma 4 26B · 4B active | 220.0 t/sFP16 | 605.0 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA B200 180GB · NVIDIA Rubin 288GB
Every report on each card, with its source: NVIDIA B200 180GB · NVIDIA Rubin 288GB