Quantization-specific throughput and VRAM requirements for hmellor/tiny-random-LlamaForCausalLM running on RTX 3060 12GB.
Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.
For full verdict logic and alternate GPUs, see the canonical compatibility page.
Open full compatibility report| Quantization | VRAM needed | VRAM available | Speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 12GB | 53 tok/s | ✅ Fits |
| Q8 | 7GB | 12GB | 41 tok/s | ✅ Fits |
| FP16 | 15GB | 12GB | 24 tok/s | ❌ Not recommended |