NVIDIA RTX 3060 12GB vs NVIDIA RTX 5090 for local LLMs
65 reports on the NVIDIA RTX 3060 12GB and 169 on the NVIDIA RTX 5090
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 5.0x higher on the NVIDIA RTX 5090 (360 GB/s on the NVIDIA RTX 3060 12GB, 1,792 on the NVIDIA RTX 5090). The estimates below compare them on the models people run most.
NVIDIA RTX 3060 12GB
- Memory
- 12GB
- Memory bandwidth
- 360 GB/s
- FP16 compute
- 51 TFLOPS
- Reports
- 65
NVIDIA RTX 5090
- Memory
- 32GB
- Memory bandwidth
- 1,792 GB/s
- FP16 compute
- 419 TFLOPS
- Reports
- 169
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 RTX 3060 12GB | NVIDIA RTX 5090 |
|---|---|---|
| Qwen3.8 27B | 1.5 t/sQ8_0, layers on CPU | 44.9 t/sQ6_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 20.3 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 13.1 t/sQ6_K, experts in RAM | 163.0 t/sQ5_K_M |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 27B | 1.5 t/sQ8_0, layers on CPU | 44.9 t/sQ6_K |
| Gemma 4 26B · 4B active | 58.8 t/sQ2_K | 114.5 t/sQ6_K |
Change the context, RAM or model in the calculator: NVIDIA RTX 3060 12GB · NVIDIA RTX 5090
Every report on each card, with its source: NVIDIA RTX 3060 12GB · NVIDIA RTX 5090