GPU — NVIDIA
NVIDIA GeForce RTX 3060 12GB
The ultimate budget entry card. 12GB of VRAM provides the vital headroom needed for Llama 3 and Stable Diffusion at minimum cost.
- VRAM
- 12GB
- TDP
- 170W
- Bandwidth
- 360GB/s
- AI Throughput
- 102TOPS
Est. Price$249.99
NVIDIA GeForce RTX 3060 12GB vs NVIDIA GeForce RTX 3090
Architect's technical teardown: VRAM capacity, memory bandwidth, TDP, and AI throughput — compared head-to-head for local LLM workloads.
★ Recommended for Local AI
GPU — NVIDIA
NVIDIA GeForce RTX 3090
The legendary used-market GOAT. 24GB VRAM at a fraction of the cost of 4090/5090. Still handles 70B models with ease.
- VRAM
- 24GB
- TDP
- 350W
- Bandwidth
- 936GB/s
- AI Throughput
- 285TOPS
Est. Price$749.99
Full Specification Matrix
| Metric | NVIDIA GeForce RTX 3060 12GB | NVIDIA GeForce RTX 3090 |
|---|---|---|
| VRAM | 12GB | 24GB |
| Memory Bandwidth | 360 GB/s | 936 GB/s |
| AI Throughput (TOPS) | 102 | 285 |
| TDP (Power Draw) | 170W | 350W |
| Est. Price | $249.99 | $749.99 |