Written by Jakub Rusinowski · Last updated January 15, 2025
Yes, but it is tight
Yes, but it is tight — InternLM 3 20B Instruct at Q4_K_M needs about 14.5 GB of the 16 GB usable on RTX 5060 Ti 16 GB Desktop (16 GB VRAM, 32 GB RAM), leaving only ~1.5 GB before the runtime starts swapping. Expect ~24.7 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: low · Recommended quantization: Q4_K_M · Estimated speed: ~24.7 tok/s
| Usable memory for models | 16 GB |
| Memory bandwidth | 448 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 16 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 42.4 GB | ✗ No | — | — | 40 GB |
| Q8_0 | 23.6 GB | ✗ No | — | — | 21.3 GB |
| Q6_K | 18.8 GB | ✗ No | — | — | 16.4 GB |
| Q5_K_M | 16.6 GB | ✗ No | — | — | 14.2 GB |
| Q4_K_M | 14.5 GB | ✓ Yes | 8K | ~24.7 tok/s | 12.1 GB |
| Q3_K_M | 10.9 GB | ✓ Yes | 32K | ~33.4 tok/s | 8.5 GB |
| Q2_K | 9 GB | ✓ Yes | 32K | ~41.4 tok/s | 6.6 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| InternLM 3 20B Instruct | 14.5 GB | ✓ Fits | ~24.7 tok/s |
| InternLM 3 8B Instruct | 6.5 GB | ✓ Fits | ~53.6 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, but it is tight — InternLM 3 20B Instruct at Q4_K_M needs about 14.5 GB of the 16 GB usable on RTX 5060 Ti 16 GB Desktop (16 GB VRAM, 32 GB RAM), leaving only ~1.5 GB before the runtime starts swapping. Expect ~24.7 tok/s (estimated), with room for about 8,192 tokens of context.
Q4_K_M — it needs about 14.5 GB of the 16 GB available, downloads as roughly 12.1 GB, and runs at an estimated 24.7 tokens/sec with up to 8K 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? | InternLM 3 model page | Check your hardware