Can I Run Yi 1.5 Family on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Newer alternative. 01.AI has not released a newer model in this library. If you are choosing today, Qwen 3 is a comparable current option. View Qwen 3 →

Written by Jakub Rusinowski · Last updated May 13, 2024

Yes — comfortably

Yes, comfortably — Yi 1.5 34B Chat at Q8_0 needs about 39.4 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~88.6 GB spare and running at ~5.1 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~5.1 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 NVIDIA A40 on RunPod — from $0.44/hr · rate checked 2026-08

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

Yi 1.5 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	71.6 GB	✓ Yes	16K	~2.7 tok/s	68.8 GB
Q8_0	39.4 GB	✓ Yes	16K	~5.1 tok/s	36.6 GB
Q6_K	31 GB	✓ Yes	16K	~6.5 tok/s	28.2 GB
Q5_K_M	27.2 GB	✓ Yes	16K	~7.4 tok/s	24.4 GB
Q4_K_M	23.6 GB	✓ Yes	16K	~8.6 tok/s	20.8 GB
Q3_K_M	17.5 GB	✓ Yes	16K	~11.9 tok/s	14.7 GB
Q2_K	14.1 GB	✓ Yes	16K	~15.1 tok/s	11.3 GB

Which Yi 1.5 Family sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Yi 1.5 34B Chat	23.6 GB	✓ Fits	~8.6 tok/s
Yi 1.5 9B Chat	6.9 GB	✓ Fits	~31.1 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