Can I Run Llama 4.5 on 96 GB system RAM?
Written by Jakub Rusinowski · Last updated June 26, 2026
Yes, but it is tight
Yes, but it is tight — Llama 4.5 Scout at Q4_K_M needs about 69.4 GB of the 76.8 GB usable on 96 GB system RAM, leaving only ~7.4 GB before the runtime starts swapping. Expect ~5.7 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: low · Recommended quantization: Q4_K_M · Estimated speed: ~5.7 tok/s
96 GB system RAM — what it gives a model
| Usable memory for models | 76.8 GB |
| Memory bandwidth | 90 GB/s |
Llama 4.5 on 96 GB system RAM: memory by quantization
| Quant | Memory needed | Fits 76.8 GB? | Max context | Est. speed | Download |
|---|
| F16 | 221.6 GB | ✗ No | — | — | 218 GB |
| Q8_0 | 119.4 GB | ✗ No | — | — | 115.8 GB |
| Q6_K | 92.9 GB | ✗ No | — | — | 89.4 GB |
| Q5_K_M | 80.8 GB | ✗ No | — | — | 77.3 GB |
| Q4_K_M | 69.4 GB | ✓ Yes | 16K | ~5.7 tok/s | 65.8 GB |
| Q3_K_M | 50 GB | ✓ Yes | 64K | ~7.7 tok/s | 46.5 GB |
| Q2_K | 39.4 GB | ✓ Yes | 64K | ~9.4 tok/s | 35.8 GB |
What to watch out for
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
- These figures assume CPU-only inference. Any discrete GPU, even an 8 GB one, will be several times faster for models that fit in its VRAM.
Recommended setup
llama.cpp (CPU build) or Ollama — both run without a GPU
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 76.8 GB of the 96 GB is treated as usable for model weights (80% — the rest is the OS and running applications).
- DDR5-5600 dual channel at 89.6 GB/s peak. CPU decode is assumed to sustain 35% of that peak, because CPU inference is not purely bandwidth-bound — it also spends real time in compute and thread synchronisation. This figure is an assumption, not a fitted constant: no CPU measurement is in the calibration set.
- CPU-only inference: no GPU is assumed. A GPU of any size will beat these figures substantially.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run Llama 4.5 on 96 GB system RAM?
Yes, but it is tight — Llama 4.5 Scout at Q4_K_M needs about 69.4 GB of the 76.8 GB usable on 96 GB system RAM, leaving only ~7.4 GB before the runtime starts swapping. Expect ~5.7 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of Llama 4.5 should I use on 96 GB system RAM?
Q4_K_M — it needs about 69.4 GB of the 76.8 GB available, downloads as roughly 65.8 GB, and runs at an estimated 5.7 tokens/sec with up to 16K of context.
What limits Llama 4.5 on 96 GB system RAM?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
llama.cpp (CPU build) or Ollama — both run without a GPU
Other RAM Capacities
Other Models on 96 GB system RAM
Llama 4.5 on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Llama 4.5 model page | Check your hardware