Can I Run Llama 3.3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Superseded model. Llama 3.3 has been superseded by Llama 4. This page is kept for reference; the newer family is a better starting point. View Llama 4 →

Written by Jakub Rusinowski · Last updated December 8, 2024

Yes — comfortably

Yes, comfortably — Llama 3.3 70B Instruct at Q3_K_M needs about 33.3 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~94.7 GB spare and running at ~6.1 tok/s (estimated), with room for about 131,072 tokens of context.

Confidence: high · Recommended quantization: Q3_K_M · Estimated speed: ~6.1 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

Llama 3.3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

QuantMemory neededFits 128 GB?Max contextEst. speedDownload
F16143.5 GB✗ No140 GB
Q8_077.9 GB✓ Yes128K~2.5 tok/s74.4 GB
Q6_K60.9 GB✓ Yes128K~3.2 tok/s57.4 GB
Q5_K_M53.1 GB✓ Yes128K~3.7 tok/s49.6 GB
Q4_K_M45.7 GB✓ Yes128K~4.4 tok/s42.3 GB
Q3_K_M33.3 GB✓ Yes128K~6.1 tok/s29.8 GB
Q2_K26.5 GB✓ Yes128K~7.7 tok/s23 GB

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 Llama 3.3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Yes, comfortably — Llama 3.3 70B Instruct at Q3_K_M needs about 33.3 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~94.7 GB spare and running at ~6.1 tok/s (estimated), with room for about 131,072 tokens of context.

Which quantization of Llama 3.3 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q3_K_M — it needs about 33.3 GB of the 128 GB available, downloads as roughly 29.8 GB, and runs at an estimated 6.1 tokens/sec with up to 128K of context.

What limits Llama 3.3 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)

Llama 3.3 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Llama 3.3 model page | Check your hardware