Can I Run Qwen3-Coder on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated September 29, 2026

Yes — comfortably

Yes, comfortably — Qwen3-Coder-Next (80B-A3B MoE) at Q8_0 needs about 88.3 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~39.7 GB spare and running at ~39.5 tok/s (estimated), with room for about 131,072 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~39.5 tok/s

See what else this hardware can run →

Buy this hardware NVIDIA DGX Spark (128GB) — 128 GB VRAM · 150 W board power Deploy in the cloud now RunPod

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

Qwen3-Coder on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

Quant	Memory needed	Fits 128 GB?	Max context	Est. speed	Download
F16	163.3 GB	✗ No	—	—	160 GB
Q8_0	88.3 GB	✓ Yes	128K	~39.5 tok/s	85 GB
Q6_K	68.9 GB	✓ Yes	128K	~46.5 tok/s	65.6 GB
Q5_K_M	60 GB	✓ Yes	128K	~50.5 tok/s	56.7 GB
Q4_K_M	51.6 GB	✓ Yes	128K	~55.1 tok/s	48.3 GB
Q3_K_M	37.4 GB	✓ Yes	256K	~65.1 tok/s	34.1 GB
Q2_K	29.6 GB	✓ Yes	256K	~72.2 tok/s	26.3 GB

Which Qwen3-Coder sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Qwen3-Coder 480B-A35B (MoE)	291.6 GB	✗ Too large	—
Qwen3-Coder-Next (80B-A3B MoE)	51.6 GB	✓ Fits	~55.1 tok/s
Qwen3-Coder 30B-A3B (MoE)	20 GB	✓ Fits	~67.9 tok/s
Qwen3-Coder 8B	6.8 GB	✓ Fits	~32.9 tok/s

What to watch out for

1 larger variant of Qwen3-Coder 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