NVIDIA P102-100 vs NVIDIA RTX 4060 for local LLMs
2 reports on the NVIDIA P102-100 and 7 on the NVIDIA RTX 4060
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 1.6x higher on the NVIDIA P102-100 (440 GB/s on the NVIDIA P102-100, 272 on the NVIDIA RTX 4060). The estimates below compare them on the models people run most.
NVIDIA P102-100
- Memory
- 10GB
- Memory bandwidth
- 440 GB/s
- FP16 compute
- 10.8 TFLOPS
- Reports
- 2
NVIDIA RTX 4060
- Memory
- 8GB
- Memory bandwidth
- 272 GB/s
- FP16 compute
- 60.5 TFLOPS
- Reports
- 7
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 P102-100 | NVIDIA RTX 4060 |
|---|---|---|
| Qwen3.8 27B | 1.9 t/sQ6_K, layers on CPU | 1.6 t/sQ6_K, layers on CPU |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 16.1 t/sQ5_K_M, experts in RAM | 14.5 t/sQ5_K_M, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 1.9 t/sQ6_K, layers on CPU | 1.6 t/sQ6_K, layers on CPU |
| Gemma 4 26B · 4B active | 8.3 t/sQ8_0, experts in RAM | 9.2 t/sQ6_K, experts in RAM |
Change the context, RAM or model in the calculator: NVIDIA P102-100 · NVIDIA RTX 4060
Every report on each card, with its source: NVIDIA P102-100 · NVIDIA RTX 4060