Can I Run Llama 3.2 Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated August 15, 2026

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

Usable memory for models	128 GB
Memory bandwidth	256 GB/s
Form factor	Mini PC
Operating system	Windows or Linux
Memory upgradeable	No — soldered

Llama 3.2 Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

Quant	Memory needed	Fits 128 GB?	Max context	Est. speed	Download
F16	181.8 GB	✗ No	—	—	177.6 GB
Q8_0	98.5 GB	✓ Yes	64K	~2 tok/s	94.4 GB
Q6_K	77 GB	✓ Yes	64K	~2.6 tok/s	72.8 GB
Q5_K_M	67.1 GB	✓ Yes	64K	~3 tok/s	62.9 GB
Q4_K_M	57.8 GB	✓ Yes	64K	~3.4 tok/s	53.6 GB
Q3_K_M	42 GB	✓ Yes	64K	~4.8 tok/s	37.9 GB
Q2_K	33.3 GB	✓ Yes	64K	~6.1 tok/s	29.2 GB

Which Llama 3.2 Family sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Llama 3.2 90B Vision Instruct	57.8 GB	✓ Fits	~3.4 tok/s
Llama 3.2 11B Vision Instruct	8.5 GB	✓ Fits	~25.6 tok/s
Llama 3.2 3B Instruct	3.7 GB	✓ Fits	~67.6 tok/s
Llama 3.2 1B Instruct	1.8 GB	✓ Fits	~146.1 tok/s

What to watch out for

• Q2_K is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
• Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.

Framework Desktop 128 GB limitations

• Memory is soldered LPDDR5X — unusually for Framework, this is the one component that cannot be upgraded.
• ROCm/Vulkan support for Strix Halo is younger than CUDA; check your runtime supports it before buying.

Recommended setup

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

How these numbers are calculated

• Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
• 128 GB unified memory at 256 GB/s, shared between CPU and GPU.
• 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 Llama 3.2 Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Yes, comfortably — Llama 3.2 90B Vision Instruct at Q2_K 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 65,536 tokens of context.

Which quantization of Llama 3.2 Family should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q2_K — it needs about 33.3 GB of the 128 GB available, downloads as roughly 29.2 GB, and runs at an estimated 6.1 tokens/sec with up to 64K of context.

What limits Llama 3.2 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

• Llama 3.2 Family on Mac mini M4 16 GB
• Llama 3.2 Family on Mac mini M4 Pro 64 GB
• Llama 3.2 Family on Beelink SER9 32 GB

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

• Llama 3.2 Vision on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
• Llama 3.3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
• Llama 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
• Llama 4.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
• MiniMax M2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)

Llama 3.2 Family on GPUs

• Llama 3.2 Family on NVIDIA GeForce RTX 5070
• Llama 3.2 Family on NVIDIA GeForce RTX 5060 Ti 8GB
• Llama 3.2 Family on NVIDIA GeForce RTX 5060
• Llama 3.2 Family on NVIDIA GeForce RTX 4070 Ti

What This Model Is Good At

• Best local LLMs for research
• Best local LLMs for document analysis
• Best local LLMs for vision

Model & Tools

• Llama 3.2 Family model page
• VRAM calculator
• Check your own hardware

← Can I Run It? | Llama 3.2 Family model page | Check your hardware