NVIDIA RTX 3060 Laptop 6GB vs NVIDIA RTX 3070 for local LLMs
2 reports on the NVIDIA RTX 3060 Laptop 6GB and 7 on the NVIDIA RTX 3070
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 33% higher on the NVIDIA RTX 3070 (336 GB/s on the NVIDIA RTX 3060 Laptop 6GB, 448 on the NVIDIA RTX 3070). The estimates below compare them on the models people run most.
- Memory
- 6GB
- Memory bandwidth
- 336 GB/s
- FP16 compute
- not on record
- Reports
- 2
- Memory
- 8GB
- Memory bandwidth
- 448 GB/s
- FP16 compute
- 81.3 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 RTX 3060 Laptop 6GB | NVIDIA RTX 3070 |
|---|---|---|
| Qwen3.8 27B | 1.5 t/sQ6_K, layers on CPU | 1.8 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 | 15.3 t/sQ5_K_M, experts in RAM | 16.1 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 | 1.5 t/sQ6_K, layers on CPU | 1.8 t/sQ6_K, layers on CPU |
| Gemma 4 26B · 4B active | 15.7 t/sQ4_K_S, experts in RAM | 10.2 t/sQ6_K, experts in RAM |
Change the context, RAM or model in the calculator: NVIDIA RTX 3060 Laptop 6GB · NVIDIA RTX 3070
Every report on each card, with its source: NVIDIA RTX 3060 Laptop 6GB · NVIDIA RTX 3070