NVIDIA RTX 3060 12GB vs NVIDIA RTX 5080 for local LLMs
65 reports on the NVIDIA RTX 3060 12GB and 29 on the NVIDIA RTX 5080
Which is faster for local LLMs?
On Qwen2.5 7B at 4-bit, the NVIDIA RTX 3060 12GB has 49.0 generation tokens/s (one run); the NVIDIA RTX 5080 has 176.6 generation tokens/s (one run); prompt processing 9984.4 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 2.7x higher on the NVIDIA RTX 5080 (360 GB/s on the NVIDIA RTX 3060 12GB, 960 on the NVIDIA RTX 5080).
- Memory
- 12GB
- Memory bandwidth
- 360 GB/s
- FP16 compute
- 51 TFLOPS
- Reports
- 65
- Memory
- 16GB
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 225 TFLOPS
- Reports
- 29
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 12GB | NVIDIA RTX 5080 |
|---|---|---|
| Qwen2.5 7B4-bit | 49.0one runOllamacontext not stated | 176.6one runPP 9984.4 (one run)Ollama16K context |
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 12GB | NVIDIA RTX 5080 |
|---|---|---|
| Qwen2.5 7B | 56.6 t/sQ4_K_S | 75.4 t/sQ8_0 |
| Qwen3.8 27B | 1.5 t/sQ8_0, layers on CPU | 62.6 t/sQ2_K |
| Qwen3.8 125B · 6B 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 | 207.0 t/sQ2_K |
| 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 | 62.6 t/sQ2_K |
| Gemma 4 26B · 4B active | 58.8 t/sQ2_K | 139.6 t/sQ3_K_S |
Change the context, RAM or model in the calculator: NVIDIA RTX 3060 12GB · NVIDIA RTX 5080
Every report on each card, with its source: NVIDIA RTX 3060 12GB · NVIDIA RTX 5080