Run Inkling-Small on M3 Ultra

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.

Speed
18
tok/s
First Token
0.9
seconds
RAM Needed
512
GB minimum
Engine
MLX
recommended
Want to run Inkling-Small faster — or step up to bigger models? Find your Mac →

Benchmark Details

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 →

MetricValue
Tokens per second18 tok/s
Time to first token0.9s
QuantizationQ4_K_M
Minimum RAM512 GB
Recommended engineMLX
Parameters276B-A12B
Benchmark date2026-08

Q4_K_M 276B-A12B MLX M3 Ultra

Setup Guide: Run Inkling-Small on M3 Ultra

The recommended engine for Inkling-Small on M3 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/inkling-small-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run inkling-small

System Requirements

To run Inkling-Small on M3 Ultra you need:

🛒 Get a Mac that runs Inkling-Small

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.

Compare More Models

See how Inkling-Small stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard