Can I Run Qwen 3.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated February 24, 2026

Yes

Yes — Qwen 3.5 122B-A10B at Q6_K needs about 103.7 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB) (~24.3 GB spare), at ~19.1 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~19.1 tok/s

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

Qwen 3.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

Quant	Memory needed	Fits 128 GB?	Max context	Est. speed	Download
F16	247.7 GB	✗ No	—	—	244 GB
Q8_0	133.3 GB	✗ No	—	—	129.6 GB
Q6_K	103.7 GB	✓ Yes	64K	~19.1 tok/s	100 GB
Q5_K_M	90.1 GB	✓ Yes	64K	~21.5 tok/s	86.5 GB
Q4_K_M	77.3 GB	✓ Yes	128K	~24.3 tok/s	73.7 GB
Q3_K_M	55.7 GB	✓ Yes	128K	~31.4 tok/s	52 GB
Q2_K	43.8 GB	✓ Yes	128K	~37.3 tok/s	40.1 GB

Which Qwen 3.5 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Qwen 3.5 397B-A17B	244.7 GB	✗ Too large	—
Qwen 3.5 122B-A10B	77.3 GB	✓ Fits	~24.3 tok/s
Qwen 3.5 35B-A3B	23.8 GB	✓ Fits	~60.3 tok/s
Qwen 3.5 27B	18.8 GB	✓ Fits	~10.9 tok/s
Qwen 3.5 9B	7.4 GB	✓ Fits	~29.7 tok/s
Qwen 3.5 4B	4.1 GB	✓ Fits	~58.2 tok/s
Qwen 3.5 2B	2.7 GB	✓ Fits	~95.6 tok/s
Qwen 3.5 0.8B	1.8 GB	✓ Fits	~162.3 tok/s

What to watch out for

1 larger variant of Qwen 3.5 does not fit and would need CPU offload or different hardware.
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 Qwen 3.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Which quantization of Qwen 3.5 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q6_K — it needs about 103.7 GB of the 128 GB available, downloads as roughly 100 GB, and runs at an estimated 19.1 tokens/sec with up to 64K of context.

What limits Qwen 3.5 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.

Can I Run Qwen 3.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

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

Qwen 3.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

Which Qwen 3.5 sizes fit

What to watch out for

Framework Desktop 128 GB limitations

Recommended setup

How these numbers are calculated

FAQ

Can I run Qwen 3.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Which quantization of Qwen 3.5 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

What limits Qwen 3.5 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Which runtime should I use?

Other Computers

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

Qwen 3.5 on GPUs

What This Model Is Good At

Model & Tools