作者： Jakub Rusinowski · 最后更新： 2024年7月23日
Yes
Yes — Llama 3.1 8B Instruct at Q8_0 needs about 10.4 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM) (~1.6 GB spare), at ~28 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~28 tok/s
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
| 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 | 17.9 GB | ✗ No | — | — | 16 GB |
| Q8_0 | 10.4 GB | ✓ Yes | 16K | ~28 tok/s | 8.5 GB |
| Q6_K | 8.4 GB | ✓ Yes | 32K | ~35 tok/s | 6.6 GB |
| Q5_K_M | 7.5 GB | ✓ Yes | 32K | ~39.6 tok/s | 5.7 GB |
| Q4_K_M | 6.7 GB | ✓ Yes | 32K | ~45.2 tok/s | 4.8 GB |
| Q3_K_M | 5.3 GB | ✓ Yes | 32K | ~59.3 tok/s | 3.4 GB |
| Q2_K | 4.5 GB | ✓ Yes | 32K | ~71.6 tok/s | 2.6 GB |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes — Llama 3.1 8B Instruct at Q8_0 needs about 10.4 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM) (~1.6 GB spare), at ~28 tok/s (estimated), with room for about 16,384 tokens of context.
Q8_0 — it needs about 10.4 GB of the 12 GB available, downloads as roughly 8.5 GB, and runs at an estimated 28 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? | Llama 3.1 Family model page | Check your hardware