Written by Jakub Rusinowski · Last updated February 4, 2025
Yes — comfortably
Yes, comfortably — Phi-4 Mini (3.8B) at Q8_0 needs about 5.9 GB of the 76.8 GB usable on 96 GB system RAM, leaving ~70.9 GB spare and running at ~14.2 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~14.2 tok/s
| Usable memory for models | 76.8 GB |
| Memory bandwidth | 90 GB/s |
| Quant | Memory needed | Fits 76.8 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 9.5 GB | ✓ Yes | 64K | ~8.1 tok/s | 7.6 GB |
| Q8_0 | 5.9 GB | ✓ Yes | 64K | ~14.2 tok/s | 4 GB |
| Q6_K | 5 GB | ✓ Yes | 64K | ~17.7 tok/s | 3.1 GB |
| Q5_K_M | 4.6 GB | ✓ Yes | 64K | ~19.9 tok/s | 2.7 GB |
| Q4_K_M | 4.2 GB | ✓ Yes | 64K | ~22.5 tok/s | 2.3 GB |
| Q3_K_M | 3.5 GB | ✓ Yes | 64K | ~29.1 tok/s | 1.6 GB |
| Q2_K | 3.1 GB | ✓ Yes | 64K | ~34.7 tok/s | 1.2 GB |
llama.cpp (CPU build) or Ollama — both run without a GPU
Yes, comfortably — Phi-4 Mini (3.8B) at Q8_0 needs about 5.9 GB of the 76.8 GB usable on 96 GB system RAM, leaving ~70.9 GB spare and running at ~14.2 tok/s (estimated), with room for about 65,536 tokens of context.
Q8_0 — it needs about 5.9 GB of the 76.8 GB available, downloads as roughly 4 GB, and runs at an estimated 14.2 tokens/sec with up to 64K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
llama.cpp (CPU build) or Ollama — both run without a GPU
← Can I Run It? | Phi-4 Mini model page | Check your hardware