Can I Run Llama 4.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated June 26, 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 4.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

Quant	Memory needed	Fits 128 GB?	Max context	Est. speed	Download
F16	221.6 GB	✗ No	—	—	218 GB
Q8_0	119.4 GB	✓ Yes	32K	~9.7 tok/s	115.8 GB
Q6_K	92.9 GB	✓ Yes	64K	~12.2 tok/s	89.4 GB
Q5_K_M	80.8 GB	✓ Yes	128K	~13.9 tok/s	77.3 GB
Q4_K_M	69.4 GB	✓ Yes	128K	~15.9 tok/s	65.8 GB
Q3_K_M	50 GB	✓ Yes	128K	~21.2 tok/s	46.5 GB
Q2_K	39.4 GB	✓ Yes	256K	~26 tok/s	35.8 GB

What to watch out for

• This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
• 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 inferred from the parameter count because this model does not publish its full attention configuration.

FAQ

Can I run Llama 4.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Yes, but it is tight — Llama 4.5 Scout at Q8_0 needs about 119.4 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving only ~8.6 GB before the runtime starts swapping. Expect ~9.7 tok/s (estimated), with room for about 32,768 tokens of context.

Which quantization of Llama 4.5 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q8_0 — it needs about 119.4 GB of the 128 GB available, downloads as roughly 115.8 GB, and runs at an estimated 9.7 tokens/sec with up to 32K of context.

What limits Llama 4.5 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 4.5 on Mac mini M4 Pro 64 GB

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

• MiniMax M2.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
• MiniMax M2.7 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
• MiniMax M3 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
• Ministral on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
• Mistral Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)

Llama 4.5 on GPUs

• Llama 4.5 on NVIDIA GeForce RTX 5090
• Llama 4.5 on Apple M4 Max
• Llama 4.5 on Apple M4
• Llama 4.5 on Apple M3 Max

What This Model Is Good At

• Best local LLMs for coding
• Best local LLMs for reasoning
• Best local LLMs for rag

Model & Tools

• Llama 4.5 model page
• VRAM calculator
• Check your own hardware

← Can I Run It? | Llama 4.5 model page | Check your hardware