Can I Run Command R Family on 128 GB system RAM?
Newer alternative. Cohere has not released a newer model in this library. If you are choosing today, Mistral Small 4 is a comparable current option.
View Mistral Small 4 →
Written by Jakub Rusinowski · Last updated April 4, 2024
Technically yes, but not recommended
It loads, but it is not worth running — Command R+ (104B) at Q6_K fits in 128 GB system RAM's 102.4 GB, yet the memory bandwidth limits it to ~0.8 tok/s (estimated), well below usable interactive speed.
Confidence: high · Recommended quantization: Q6_K · Estimated speed: ~0.8 tok/s
128 GB system RAM — what it gives a model
| Usable memory for models | 102.4 GB |
| Memory bandwidth | 90 GB/s |
Command R Family on 128 GB system RAM: memory by quantization
| Quant | Memory needed | Fits 102.4 GB? | Max context | Est. speed | Download |
|---|
| F16 | 210.9 GB | ✗ No | — | — | 208 GB |
| Q8_0 | 113.4 GB | ✗ No | — | — | 110.5 GB |
| Q6_K | 88.2 GB | ✓ Yes | 32K | ~0.8 tok/s | 85.3 GB |
| Q5_K_M | 76.7 GB | ✓ Yes | 64K | ~0.9 tok/s | 73.7 GB |
| Q4_K_M | 65.7 GB | ✓ Yes | 64K | ~1 tok/s | 62.8 GB |
| Q3_K_M | 47.3 GB | ✓ Yes | 64K | ~1.5 tok/s | 44.3 GB |
| Q2_K | 37.1 GB | ✓ Yes | 64K | ~1.9 tok/s | 34.2 GB |
Which Command R Family sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|
| Command R+ (104B) | 65.7 GB | ✓ Fits | ~1 tok/s |
| Command R (35B) | 32.7 GB | ✓ Fits | ~2.5 tok/s |
What to watch out for
- At ~0.8 tok/s this loads but is too slow for interactive use — expect roughly 75 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 Command R Family on 128 GB system RAM?
It loads, but it is not worth running — Command R+ (104B) at Q6_K fits in 128 GB system RAM's 102.4 GB, yet the memory bandwidth limits it to ~0.8 tok/s (estimated), well below usable interactive speed.
Which quantization of Command R Family should I use on 128 GB system RAM?
Q6_K — it needs about 88.2 GB of the 102.4 GB available, downloads as roughly 85.3 GB, and runs at an estimated 0.8 tokens/sec with up to 32K of context.
What limits Command R Family 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 0.8 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
Command R Family on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Command R Family model page | Check your hardware