NVIDIA Nemotron-3-super-120B-A12B on Apple M4 Ultra (192GB)
Yes — M4 Ultra (192GB) runs NVIDIA Nemotron-3-super-120B-A12B excellently at Q4_K_M — 51 tok/s. 192 GB VRAM with plenty of headroom.
Model Size
120B
Device VRAM
192 GB
Bandwidth
819 GB/s
Quantization
Q4_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for NVIDIA Nemotron-3-super-120B-A12B on Apple M4 Ultra (192GB) at Q4_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q4_K_M | 51 tok/s | 157ms | ✓ Yes | Excellent | estimated |
Notes
Q4_K_M
Q4_K_M fits in 192GB with 122GB headroom. MoE model: 120B total params, ~12B active per token. Full expert pool still must load.
About NVIDIA Nemotron-3-super-120B-A12B
NVIDIA Nemotron-3-super-120B-A12B (120B) is a chat, coding, reasoning, multi-purpose model. MoE architecture with 120B total parameters and roughly 12B active per token. Requires VRAM for the full expert pool but decodes more like a smaller model once loaded. Native 131K context with 1M-token extension support.
View all NVIDIA Nemotron-3-super-120B-A12B hardware options →About Apple M4 Ultra (192GB)
Apple M4 Ultra (192GB) has 192 GB at 819 GB/s. Available in Mac Studio, Mac Pro.
See all models Apple M4 Ultra (192GB) can run →Estimate method: Estimated from MoE benchmark reports and bandwidth scaling for 12B-active models. Reference hardware source: github.com (2026-03-24)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.