Yes — Nemotron 3.5 Lightning (30B-A3B) runs at 45 tok/s on M6 with 32 GB RAM using Q4_K_M quantization via llama.cpp. A capable open-source LLM with 30B-A3B parameters.
Want to run Nemotron 3.5 Lightning faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Nemotron 3.5 Lightning on M6 using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →
| Metric | Value |
|---|---|
| Tokens per second | 45 tok/s |
| Time to first token | — |
| Quantization | Q4_K_M |
| Minimum RAM | 32 GB |
| Recommended engine | llama.cpp |
| Parameters | 30B-A3B |
| Benchmark date | 2026-10 |
Q4_K_M 30B-A3B llama.cpp M6
The recommended engine for Nemotron 3.5 Lightning on M6 is llama.cpp. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~32 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|
To run Nemotron 3.5 Lightning on M6 you need:
Nemotron 3.5 Lightning needs about 32 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how Nemotron 3.5 Lightning stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard