Can I Run Mistral Small 4 on 96 GB system RAM?
Written by Jakub Rusinowski · Last updated March 16, 2026
Yes — comfortably
Yes, comfortably — Mistral Small 4 119B-A6.5B at Q3_K_M needs about 54.4 GB of the 76.8 GB usable on 96 GB system RAM, leaving ~22.4 GB spare and running at ~6.1 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: medium · Recommended quantization: Q3_K_M · Estimated speed: ~6.1 tok/s
96 GB system RAM — what it gives a model
| Usable memory for models | 76.8 GB |
| Memory bandwidth | 90 GB/s |
Mistral Small 4 on 96 GB system RAM: memory by quantization
| Quant | Memory needed | Fits 76.8 GB? | Max context | Est. speed | Download |
|---|
| F16 | 241.7 GB | ✗ No | — | — | 238 GB |
| Q8_0 | 130.1 GB | ✗ No | — | — | 126.4 GB |
| Q6_K | 101.2 GB | ✗ No | — | — | 97.6 GB |
| Q5_K_M | 88 GB | ✗ No | — | — | 84.3 GB |
| Q4_K_M | 75.5 GB | ✓ Yes | 8K | ~4.5 tok/s | 71.8 GB |
| Q3_K_M | 54.4 GB | ✓ Yes | 64K | ~6.1 tok/s | 50.7 GB |
| Q2_K | 42.8 GB | ✓ Yes | 64K | ~7.6 tok/s | 39.1 GB |
What to watch out for
- Q3_K_M is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
- 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 Mistral Small 4 on 96 GB system RAM?
Yes, comfortably — Mistral Small 4 119B-A6.5B at Q3_K_M needs about 54.4 GB of the 76.8 GB usable on 96 GB system RAM, leaving ~22.4 GB spare and running at ~6.1 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of Mistral Small 4 should I use on 96 GB system RAM?
Q3_K_M — it needs about 54.4 GB of the 76.8 GB available, downloads as roughly 50.7 GB, and runs at an estimated 6.1 tokens/sec with up to 64K of context.
What limits Mistral Small 4 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
Mistral Small 4 on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Mistral Small 4 model page | Check your hardware