Can I Run GPT-OSS on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated August 15, 2026

Yes, but it is tight

Yes, but it is tight — GPT-oss 120B at Q8_0 needs about 125.5 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving only ~2.5 GB before the runtime starts swapping. Expect ~31.2 tok/s (estimated), with room for about 32,768 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~31.2 tok/s

Buy This HardwareApple Mac Studio M4 Max — 128 GB VRAM · 35 W board power Deploy in the Cloud NowRunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

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

GPT-OSS on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

Quant	Memory needed	Fits 128 GB?	Max context	Est. speed	Download
F16	235 GB	✗ No	—	—	233.6 GB
Q8_0	125.5 GB	✓ Yes	32K	~31.2 tok/s	124.1 GB
Q6_K	97.2 GB	✓ Yes	128K	~39.1 tok/s	95.8 GB
Q5_K_M	84.2 GB	✓ Yes	128K	~44.2 tok/s	82.8 GB
Q4_K_M	71.9 GB	✓ Yes	128K	~50.4 tok/s	70.5 GB
Q3_K_M	51.2 GB	✓ Yes	128K	~66 tok/s	49.8 GB
Q2_K	39.8 GB	✓ Yes	128K	~79.7 tok/s	38.4 GB

Which GPT-OSS sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
GPT-oss 120B	71.9 GB	✓ Fits	~50.4 tok/s
GPT-OSS 20B	13.8 GB	✓ Fits	~68.4 tok/s

What to watch out for

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