Can I Run Nemotron 70B on 128 GB system RAM?
Superseded model. Nemotron 70B has been superseded by Nemotron 3 Super. This page is kept for reference; the newer family is a better starting point.
View Nemotron 3 Super →
Written by Jakub Rusinowski · Last updated October 15, 2024
Technically yes, but not recommended
It loads, but it is not worth running — Nemotron 70B Instruct at Q8_0 fits in 128 GB system RAM's 102.4 GB, yet the memory bandwidth limits it to ~0.9 tok/s (estimated), well below usable interactive speed.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~0.9 tok/s
128 GB system RAM — what it gives a model
| Usable memory for models | 102.4 GB |
| Memory bandwidth | 90 GB/s |
Nemotron 70B on 128 GB system RAM: memory by quantization
| Quant | Memory needed | Fits 102.4 GB? | Max context | Est. speed | Download |
|---|
| F16 | 144.7 GB | ✗ No | — | — | 141.2 GB |
| Q8_0 | 78.5 GB | ✓ Yes | 64K | ~0.9 tok/s | 75 GB |
| Q6_K | 61.4 GB | ✓ Yes | 64K | ~1.1 tok/s | 57.9 GB |
| Q5_K_M | 53.5 GB | ✓ Yes | 64K | ~1.3 tok/s | 50 GB |
| Q4_K_M | 46.1 GB | ✓ Yes | 64K | ~1.5 tok/s | 42.6 GB |
| Q3_K_M | 33.6 GB | ✓ Yes | 64K | ~2.1 tok/s | 30.1 GB |
| Q2_K | 26.7 GB | ✓ Yes | 64K | ~2.7 tok/s | 23.2 GB |
What to watch out for
- At ~0.9 tok/s this loads but is too slow for interactive use — expect roughly 67 seconds per 60 tokens.
- 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.
- 102.4 GB of the 128 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 Nemotron 70B on 128 GB system RAM?
It loads, but it is not worth running — Nemotron 70B Instruct at Q8_0 fits in 128 GB system RAM's 102.4 GB, yet the memory bandwidth limits it to ~0.9 tok/s (estimated), well below usable interactive speed.
Which quantization of Nemotron 70B should I use on 128 GB system RAM?
Q8_0 — it needs about 78.5 GB of the 102.4 GB available, downloads as roughly 75 GB, and runs at an estimated 0.9 tokens/sec with up to 64K of context.
What limits Nemotron 70B on 128 GB system RAM?
Memory bandwidth. The model fits, but at 89.6 GB/s it can only be read fast enough for roughly 0.9 tokens/sec.
Which runtime should I use?
llama.cpp (CPU build) or Ollama — both run without a GPU
Other RAM Capacities
Other Models on 128 GB system RAM
Nemotron 70B on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Nemotron 70B model page | Check your hardware