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 models102.4 GB
Memory bandwidth90 GB/s

Command R Family on 128 GB system RAM: memory by quantization

QuantMemory neededFits 102.4 GB?Max contextEst. speedDownload
F16210.9 GB✗ No208 GB
Q8_0113.4 GB✗ No110.5 GB
Q6_K88.2 GB✓ Yes32K~0.8 tok/s85.3 GB
Q5_K_M76.7 GB✓ Yes64K~0.9 tok/s73.7 GB
Q4_K_M65.7 GB✓ Yes64K~1 tok/s62.8 GB
Q3_K_M47.3 GB✓ Yes64K~1.5 tok/s44.3 GB
Q2_K37.1 GB✓ Yes64K~1.9 tok/s34.2 GB

Which Command R Family sizes fit

VariantNeeds at Q4_K_MFits?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

Recommended setup

llama.cpp (CPU build) or Ollama — both run without a GPU

How these numbers are calculated

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