Yes — Inkling-Small (276B-A12B) runs at 18 tok/s on M3 Ultra with 512 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.9s. A capable open-source LLM with 276B-A12B parameters.
Want to run Inkling-Small faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Inkling-Small on M3 Ultra 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 | 18 tok/s |
| Time to first token | 0.9s |
| Quantization | Q4_K_M |
| Minimum RAM | 512 GB |
| Recommended engine | MLX |
| Parameters | 276B-A12B |
| Benchmark date | 2026-08 |
Q4_K_M 276B-A12B MLX M3 Ultra
The recommended engine for Inkling-Small on M3 Ultra is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
To run Inkling-Small on M3 Ultra you need:
Inkling-Small needs about 512 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 our benchmarks free.
See how Inkling-Small stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard