Can I Run GPT-OSS on 96 GB system RAM?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026
Yes, but it is tight
Yes, but it is tight — GPT-OSS 120B at Q4_K_M needs about 71.6 GB of the 76.8 GB usable on 96 GB system RAM, leaving only ~5.2 GB before the runtime starts swapping. Expect ~19.7 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: medium · Recommended quantization: Q4_K_M · Estimated speed: ~19.7 tok/s
Get a personalized upgrade path →
lub porównaj w Vast.ai od $0.77/godz. (typical low · varies)
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
96 GB system RAM — what it gives a model
| Usable memory for models | 76.8 GB |
| Memory bandwidth | 90 GB/s |
GPT-OSS on 96 GB system RAM: memory by quantization
| Quant | Memory needed | Fits 76.8 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 234.7 GB | ✗ No | — | — | 233.6 GB |
| Q8_0 | 125.2 GB | ✗ No | — | — | 124.1 GB |
| Q6_K | 96.9 GB | ✗ No | — | — | 95.8 GB |
| Q5_K_M | 83.9 GB | ✗ No | — | — | 82.8 GB |
| Q4_K_M | 71.6 GB | ✓ Yes | 128K | ~19.7 tok/s | 70.5 GB |
| Q3_K_M | 50.9 GB | ✓ Yes | 128K | ~26.8 tok/s | 49.8 GB |
| Q2_K | 39.5 GB | ✓ Yes | 128K | ~33.5 tok/s | 38.4 GB |
Which GPT-OSS sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| GPT-OSS 120B | 71.6 GB | ✓ Fits | ~19.7 tok/s |
| GPT-OSS 20B | 13.6 GB | ✓ Fits | ~27.5 tok/s |
What to watch out for
- 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 computed from this model's published attention configuration.
FAQ
Can I run GPT-OSS on 96 GB system RAM?
Yes, but it is tight — GPT-OSS 120B at Q4_K_M needs about 71.6 GB of the 76.8 GB usable on 96 GB system RAM, leaving only ~5.2 GB before the runtime starts swapping. Expect ~19.7 tok/s (estimated), with room for about 131,072 tokens of context.
Which quantization of GPT-OSS should I use on 96 GB system RAM?
Q4_K_M — it needs about 71.6 GB of the 76.8 GB available, downloads as roughly 70.5 GB, and runs at an estimated 19.7 tokens/sec with up to 128K of context.
What limits GPT-OSS 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
- Granite 3.0 on 96 GB system RAM
- IBM Granite 4.0 on 96 GB system RAM
- IBM Granite 4.1 on 96 GB system RAM
- IBM Granite 4.2 on 96 GB system RAM
- InternLM 3 on 96 GB system RAM
GPT-OSS on GPUs
- GPT-OSS on NVIDIA GeForce RTX 5080
- GPT-OSS on NVIDIA GeForce RTX 5070 Ti
- GPT-OSS on NVIDIA GeForce RTX 5070
- GPT-OSS on NVIDIA GeForce RTX 5060 Ti 16GB
What This Model Is Good At
- Best local LLMs for general assistant
- Best local LLMs for document analysis
- Best local LLMs for enterprise assistant