Written by Jakub Rusinowski · Last updated May 13, 2024
Yes, but it is tight
Yes, but it is tight — Yi 1.5 9B Chat at Q8_0 needs about 11 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM), leaving only ~1 GB before the runtime starts swapping. Expect ~26 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~26 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 | 19.3 GB | ✗ No | — | — | 17.7 GB |
| Q8_0 | 11 GB | ✓ Yes | 16K | ~26 tok/s | 9.4 GB |
| Q6_K | 8.8 GB | ✓ Yes | 16K | ~32.7 tok/s | 7.2 GB |
| Q5_K_M | 7.9 GB | ✓ Yes | 16K | ~37.2 tok/s | 6.3 GB |
| Q4_K_M | 6.9 GB | ✓ Yes | 16K | ~42.6 tok/s | 5.3 GB |
| Q3_K_M | 5.4 GB | ✓ Yes | 16K | ~56.6 tok/s | 3.8 GB |
| Q2_K | 4.5 GB | ✓ Yes | 16K | ~69 tok/s | 2.9 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Yi 1.5 34B Chat | 23.6 GB | ✗ Too large | — |
| Yi 1.5 9B Chat | 6.9 GB | ✓ Fits | ~42.6 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, but it is tight — Yi 1.5 9B Chat at Q8_0 needs about 11 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM), leaving only ~1 GB before the runtime starts swapping. Expect ~26 tok/s (estimated), with room for about 16,384 tokens of context.
Q8_0 — it needs about 11 GB of the 12 GB available, downloads as roughly 9.4 GB, and runs at an estimated 26 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? | Yi 1.5 Family model page | Check your hardware