Written by Jakub Rusinowski · Last updated October 21, 2024
Yes
Yes — Granite 3.0 8B Instruct at Q8_0 needs about 10.6 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM) (~1.4 GB spare), at ~27.6 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~27.6 tok/s
| Usable memory for models | 12 GB |
| Memory bandwidth | 360 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 12 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 18.1 GB | ✗ No | — | — | 16 GB |
| Q8_0 | 10.6 GB | ✓ Yes | 16K | ~27.6 tok/s | 8.5 GB |
| Q6_K | 8.7 GB | ✓ Yes | 16K | ~34.4 tok/s | 6.6 GB |
| Q5_K_M | 7.8 GB | ✓ Yes | 32K | ~38.9 tok/s | 5.7 GB |
| Q4_K_M | 7 GB | ✓ Yes | 32K | ~44.2 tok/s | 4.8 GB |
| Q3_K_M | 5.6 GB | ✓ Yes | 32K | ~57.6 tok/s | 3.4 GB |
| Q2_K | 4.8 GB | ✓ Yes | 32K | ~69.1 tok/s | 2.6 GB |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes — Granite 3.0 8B Instruct at Q8_0 needs about 10.6 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM) (~1.4 GB spare), at ~27.6 tok/s (estimated), with room for about 16,384 tokens of context.
Q8_0 — it needs about 10.6 GB of the 12 GB available, downloads as roughly 8.5 GB, and runs at an estimated 27.6 tokens/sec with up to 16K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
← Can I Run It? | Granite 3.0 model page | Check your hardware