NVIDIA RTX 3060 Laptop 6GB vs NVIDIA RTX 3090 Ti for local LLMs
2 reports on the NVIDIA RTX 3060 Laptop 6GB and 8 on the NVIDIA RTX 3090 Ti
Which is faster for local LLMs?
On LFM3 1.7B at 8-bit, the NVIDIA RTX 3060 Laptop 6GB has 91.3 generation tokens/s (one run); prompt processing 5257.7 tokens/s (one run); the NVIDIA RTX 3090 Ti has 329.0 generation tokens/s (one run); prompt processing 20648.6 tokens/s (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 3.0x higher on the NVIDIA RTX 3090 Ti (336 GB/s on the NVIDIA RTX 3060 Laptop 6GB, 1,008 on the NVIDIA RTX 3090 Ti).
- Memory
- 6GB
- Memory bandwidth
- 336 GB/s
- FP16 compute
- not on record
- Reports
- 2
- Memory
- 24GB
- Memory bandwidth
- 1,008 GB/s
- FP16 compute
- 160 TFLOPS
- Reports
- 8
Measured on both
Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | NVIDIA RTX 3060 Laptop 6GB | NVIDIA RTX 3090 Ti |
|---|---|---|
| LFM3 1.7B8-bit | 91.3one runPP 5257.7 (one run)engine not statedcontext not stated | 329.0one runPP 20648.6 (one run)llama.cppcontext not stated |
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. Where a model was also measured above, the measurement wins.
| Model | NVIDIA RTX 3060 Laptop 6GB | NVIDIA RTX 3090 Ti |
|---|---|---|
| LFM3 1.7B | 10.1 t/sFP16, layers on CPU | 163.1 t/sFP16 |
| Qwen3.8 27B | 1.5 t/sQ6_K, layers on CPU | 36.5 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 19.6 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 15.3 t/sQ5_K_M, experts in RAM | 129.3 t/sQ4_K_S |
| 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 | 36.5 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 15.7 t/sQ4_K_S, experts in RAM | 82.3 t/sQ5_K_S |
Change the context, RAM or model in the calculator: NVIDIA RTX 3060 Laptop 6GB · NVIDIA RTX 3090 Ti
Every report on each card, with its source: NVIDIA RTX 3060 Laptop 6GB · NVIDIA RTX 3090 Ti