Nemotron · 30B · MoE
Can you run NVIDIA Nemotron Cascade 2 30B-A3B locally?
NVIDIA Nemotron Cascade 2 30B-A3B is a mixture-of-experts model with 30B parameters, 3B active per token. At 4-bit or better it runs on 55 of the 120 hardware configurations listed here; the smallest is the RTX 5090 (32 GB). On a 128 GB DGX Spark it runs at Q6_K, at roughly 63 tokens per second (our est.).
Data as of 2 November 2026
Fastest machines for NVIDIA Nemotron Cascade 2 30B-A3B
Every machine that runs it, fastest first. Filter by type; your machine is marked. Compare machines running it side by side
- 1RTX 5090Graphics card · 32 GB~411 tok/s our est.Q6_K · 26 of 31 GB
- 22x RTX 5090Graphics card · 64 GB~411 tok/s our est.Q6_K · 26 of 62 GB
- 3RTX PRO 6000 BlackwellGraphics card · 96 GB~411 tok/s our est.Q6_K · 26 of 95 GB
- 42x RTX PRO 6000 BlackwellGraphics card · 192 GB~411 tok/s our est.Q6_K · 26 of 190 GB
- 52x RTX 4090Graphics card · 48 GB~231 tok/s our est.Q6_K · 26 of 46 GB
- 62x RTX 3090 TiGraphics card · 48 GB~231 tok/s our est.Q6_K · 26 of 46 GB
- 72x RX 7900 XTXGraphics card · 48 GB~220 tok/s our est.Q6_K · 26 of 46 GB
- 82x RTX 3090Graphics card · 48 GB~215 tok/s our est.Q6_K · 26 of 46 GB
- 9M3 UltraMac · 96–512 GB · 5 variants~188 tok/s our est.Q6_K · 26 GB
- 10M2 UltraMac · 64–192 GB · 7 variants~183 tok/s our est.Q6_K · 26 GB
- 11M1 UltraMac · 64–128 GB · 4 variants~183 tok/s our est.Q6_K · 26 GB
- 12M4 MaxMac · 48–128 GB · 3 variants~125 tok/s our est.Q6_K · 26 GB
- 13M3 MaxMac · 48–128 GB · 3 variants~92 tok/s our est.Q6_K · 26 GB
- 14M2 MaxMac · 64–96 GB · 3 variants~92 tok/s our est.Q6_K · 26 GB
- 15M1 MaxMac · 64 GB · 2 variants~92 tok/s our est.Q6_K · 26 GB
- 16M3 Max · 96 GB · 30cMac · 96 GB~69 tok/s our est.Q6_K · 26 of 72 GB
- 17M4 ProMac · 48–64 GB · 4 variants~63 tok/s our est.Q6_K · 26 GB
- 18DGX Spark (GB10)AI mini PC · 128 GB~63 tok/s our est.Q6_K · 26 of 122 GB
- 19Ryzen AI Max+ 395AI mini PC · 64–128 GB · 2 variants~59 tok/s our est.Q6_K · 26 GB
- 20M5 MaxMac · 48–128 GB · 3 variantsno estimateQ6_K · 26 GB
- 21M5 ProMac · 48–64 GB · 4 variantsno estimateQ6_K · 26 GB
- 22M5 UltraMac · 96–512 GB · 5 variantsno estimateQ6_K · 26 GB
Too big for 65 machines
M5 Max · 36 GB · 32c, M4 Max · 36 GB · 32c, M3 Max · 36 GB · 30c, M3 Pro · 36 GB, RTX 4090, RTX 3090 Ti, RTX 3090, RX 7900 XTX, M2 Max · 32 GB · 38c, M2 Max · 32 GB · 30c, M1 Max · 32 GB · 32c, M1 Max · 32 GB · 24c, M2 Pro · 32 GB, M1 Pro · 32 GB, M6 · 32 GB · 12c, M5 · 32 GB · 10c, M5 · 32 GB · 8c, M4 · 32 GB, RX 7900 XT, M5 Pro · 24 GB · 20c, M5 Pro · 24 GB · 16c, M4 Pro · 24 GB · 20c, M4 Pro · 24 GB · 16c, M6 · 24 GB · 12c, M6 · 24 GB · 10c, M5 · 24 GB · 10c, M5 · 24 GB · 8c, M4 · 24 GB, M3 · 24 GB, M2 · 24 GB, RTX 5080, RTX 5070 Ti, RTX 5060 Ti, RTX 4080 SUPER, RTX 4080, RTX 4070 Ti SUPER, RTX 4060 Ti, Tesla T4, Tesla P100, RX 9070 XT, RX 9060 XT, M3 Pro · 18 GB, RTX 5070, RTX 4070 Ti, RTX 4070 SUPER, RTX 4070, RTX 3060, M2 Pro · 16 GB, M1 Pro · 16 GB, M6 · 16 GB · 12c, M6 · 16 GB · 10c, M5 · 16 GB · 10c, M5 · 16 GB · 8c, M4 · 16 GB, M3 · 16 GB, M2 · 16 GB, M1 · 16 GB, RTX 5060, RTX 4060, RTX 3070, RTX 3060 Ti, RTX 2070, M3 · 8 GB, M2 · 8 GB, M1 · 8 GB. NVIDIA Nemotron Cascade 2 30B-A3B needs about 26 GB at its smallest build.
Speeds are single-user decode estimates, not measurements. "ModelFit est." comes from ModelFit's model fitted on published runs (CC BY 4.0); "our est." is memory bandwidth divided by bytes read per token, times 0.55. Memory is what the best build needs, against what the machine can give a model. Method
About the model
- Parameters
- 30B
- Active per token
- 3B
- Type
- Mixture of experts
- Good for
- Reasoning, Math, Agentic tasks
Builds and how to run them
| Quantization | Load | Min. RAM | Command |
|---|---|---|---|
| Q6_K | 24 GB | 36 GB | ollama run nemotron-cascade-2:30b |
Load, minimum RAM and Ollama commands: ModelFit, CC BY 4.0. Load is memory with the model loaded, before long contexts.
Questions
Can I run NVIDIA Nemotron Cascade 2 30B-A3B on a Mac?
Yes on a Mac with enough memory: the smallest Apple configuration listed here that runs it at 4-bit or better is the M5 Max · 48 GB · 40c.
How much memory does NVIDIA Nemotron Cascade 2 30B-A3B need?
About 26 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.
Does NVIDIA Nemotron Cascade 2 30B-A3B run on a DGX Spark?
Yes, at Q6_K. The Spark has 128 GB of unified memory, about 121.6 GB usable.