Can I Run Nemotron Cascade 2 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

作者： Jakub Rusinowski · 最后更新： 2026年9月11日

Yes — comfortably

Yes, comfortably — Nemotron-Cascade 2 30B-A3B at Q8_0 needs about 36.2 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~91.8 GB spare and running at ~38 tok/s (estimated), with room for about 262,144 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~38 tok/s

Buy This HardwareApple MacBook Pro M5 Pro — 64 GB VRAM · 30 W board power Deploy in the Cloud NowNVIDIA 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

Nemotron Cascade 2 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

Quant	Memory needed	Fits 128 GB?	Max context	Est. speed	Download
F16	65.8 GB	✓ Yes	256K	~23 tok/s	63.2 GB
Q8_0	36.2 GB	✓ Yes	256K	~38 tok/s	33.6 GB
Q6_K	28.5 GB	✓ Yes	256K	~45.6 tok/s	25.9 GB
Q5_K_M	25 GB	✓ Yes	256K	~50.3 tok/s	22.4 GB
Q4_K_M	21.7 GB	✓ Yes	256K	~55.6 tok/s	19.1 GB
Q3_K_M	16.1 GB	✓ Yes	256K	~67.9 tok/s	13.5 GB
Q2_K	13 GB	✓ Yes	256K	~77.2 tok/s	10.4 GB

Which Nemotron Cascade 2 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Nemotron Cascade 2 70B (Unverified Listing)	45.4 GB	✓ Fits	~4.4 tok/s
Nemotron-Cascade 2 30B-A3B	21.7 GB	✓ Fits	~55.6 tok/s

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