NVIDIA RTX 3060 12GB vs NVIDIA RTX 3080 Laptop 16GB for local LLMs
46 reports on the NVIDIA RTX 3060 12GB and 2 on the NVIDIA RTX 3080 Laptop 16GB
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. 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
- 46
NVIDIA RTX 3080 Laptop 16GB
- Memory
- 16GB
- Memory bandwidth
- not on record
- FP16 compute
- not on record
- Reports
- 2
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 3080 Laptop 16GB |
|---|---|---|
| Qwen3.8 27B | 1.5 t/sQ8_0, layers on CPU | no estimateQ2_K |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 13.1 t/sQ6_K, experts in RAM | no estimateQ2_K |
| Qwen3.6 27B | 1.5 t/sQ8_0, layers on CPU | no estimateQ2_K |
| Gemma 4 26B · 4B active | 58.8 t/sQ2_K | no estimateQ3_K_S |
Change the context, RAM or model in the calculator: NVIDIA RTX 3060 12GB · NVIDIA RTX 3080 Laptop 16GB
Every report on each card, with its source: NVIDIA RTX 3060 12GB · NVIDIA RTX 3080 Laptop 16GB