Can I Run Nemotron 70B on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Superseded model. Nemotron 70B has been superseded by Nemotron 3 Super. This page is kept for reference; the newer family is a better starting point.
View Nemotron 3 Super →
Written by Jakub Rusinowski · Last updated October 15, 2024
Yes — comfortably
Yes, comfortably — Nemotron 70B Instruct at Q3_K_M needs about 33.6 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~94.4 GB spare and running at ~6 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q3_K_M · Estimated speed: ~6 tok/s
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 70B on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|
| F16 | 144.7 GB | ✗ No | — | — | 141.2 GB |
| Q8_0 | 78.5 GB | ✓ Yes | 64K | ~2.5 tok/s | 75 GB |
| Q6_K | 61.4 GB | ✓ Yes | 64K | ~3.2 tok/s | 57.9 GB |
| Q5_K_M | 53.5 GB | ✓ Yes | 64K | ~3.7 tok/s | 50 GB |
| Q4_K_M | 46.1 GB | ✓ Yes | 64K | ~4.3 tok/s | 42.6 GB |
| Q3_K_M | 33.6 GB | ✓ Yes | 64K | ~6 tok/s | 30.1 GB |
| Q2_K | 26.7 GB | ✓ Yes | 64K | ~7.7 tok/s | 23.2 GB |
What to watch out for
- Q3_K_M is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
- 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
Can I run Nemotron 70B on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Yes, comfortably — Nemotron 70B Instruct at Q3_K_M needs about 33.6 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~94.4 GB spare and running at ~6 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of Nemotron 70B should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Q3_K_M — it needs about 33.6 GB of the 128 GB available, downloads as roughly 30.1 GB, and runs at an estimated 6 tokens/sec with up to 64K of context.
What limits Nemotron 70B 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 70B on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | Nemotron 70B model page | Check your hardware