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

Written by Jakub Rusinowski · Last updated March 15, 2026

Yes — comfortably

Yes, comfortably — Nemotron Cascade 2 70B at Q3_K_M needs about 33 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~95 GB spare and running at ~6.1 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: medium · Recommended quantization: Q3_K_M · Estimated speed: ~6.1 tok/s

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

Usable memory for models128 GB
Memory bandwidth256 GB/s
Form factorMini PC
Operating systemWindows or Linux
Memory upgradeableNo — soldered

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

QuantMemory neededFits 128 GB?Max contextEst. speedDownload
F16143.2 GB✗ No140 GB
Q8_077.6 GB✓ Yes64K~2.5 tok/s74.4 GB
Q6_K60.6 GB✓ Yes64K~3.3 tok/s57.4 GB
Q5_K_M52.8 GB✓ Yes64K~3.7 tok/s49.6 GB
Q4_K_M45.4 GB✓ Yes64K~4.4 tok/s42.3 GB
Q3_K_M33 GB✓ Yes64K~6.1 tok/s29.8 GB
Q2_K26.2 GB✓ Yes64K~7.8 tok/s23 GB

Which Nemotron Cascade 2 sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Nemotron Cascade 2 70B45.4 GB✓ Fits~4.4 tok/s
Nemotron Cascade 2 30B20.7 GB✓ Fits~9.9 tok/s

What to watch out for

Framework Desktop 128 GB limitations

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

FAQ

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

Yes, comfortably — Nemotron Cascade 2 70B at Q3_K_M needs about 33 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~95 GB spare and running at ~6.1 tok/s (estimated), with room for about 65,536 tokens of context.

Which quantization of Nemotron Cascade 2 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q3_K_M — it needs about 33 GB of the 128 GB available, downloads as roughly 29.8 GB, and runs at an estimated 6.1 tokens/sec with up to 64K of context.

What limits Nemotron Cascade 2 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.

Which runtime should I use?

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

Other Computers

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

Nemotron Cascade 2 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Nemotron Cascade 2 model page | Check your hardware