Can I Run Command R Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

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

Yes — comfortably

Yes, comfortably — Command R+ (104B) at Q2_K needs about 37.1 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~90.9 GB spare and running at ~5.4 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: high · Recommended quantization: Q2_K · Estimated speed: ~5.4 tok/s

Framework Desktop (Ryzen AI Max+ 395, 128 GB) — what it gives a model

Usable memory for models128 GB
Memory bandwidth256 GB/s
Form factorMini PC
Operating systemWindows or Linux
Memory upgradeableNo — soldered

Command R Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

QuantMemory neededFits 128 GB?Max contextEst. speedDownload
F16210.9 GB✗ No208 GB
Q8_0113.4 GB✓ Yes32K~1.7 tok/s110.5 GB
Q6_K88.2 GB✓ Yes64K~2.2 tok/s85.3 GB
Q5_K_M76.7 GB✓ Yes64K~2.6 tok/s73.7 GB
Q4_K_M65.7 GB✓ Yes64K~3 tok/s62.8 GB
Q3_K_M47.3 GB✓ Yes64K~4.2 tok/s44.3 GB
Q2_K37.1 GB✓ Yes64K~5.4 tok/s34.2 GB

Which Command R Family sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Command R+ (104B)65.7 GB✓ Fits~3 tok/s
Command R (35B)32.7 GB✓ Fits~7.1 tok/s

What to watch out for

Framework Desktop 128 GB limitations

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

FAQ

Can I run Command R Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Yes, comfortably — Command R+ (104B) at Q2_K needs about 37.1 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~90.9 GB spare and running at ~5.4 tok/s (estimated), with room for about 65,536 tokens of context.

Which quantization of Command R Family should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q2_K — it needs about 37.1 GB of the 128 GB available, downloads as roughly 34.2 GB, and runs at an estimated 5.4 tokens/sec with up to 64K of context.

What limits Command R Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

Other Computers

Other Models on Framework Desktop (Ryzen AI Max+ 395, 128 GB)

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