Run Laguna S 2.1 on M5 Ultra

Yes — Laguna S 2.1 (118B) runs at 53 tok/s on M5 Ultra with 96 GB RAM using Q4_K_M quantization via MLX. First token latency is Nones. A capable open-source LLM with 118B parameters.

Speed
estimated53
tok/s
First Token
estimatedNone
seconds
RAM Needed
96
GB minimum
Engine
MLX
recommended
Want to run Laguna S 2.1 faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Laguna S 2.1 on M5 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 second53 tok/s
Time to first tokenNones
QuantizationQ4_K_M
Minimum RAM96 GB
Recommended engineMLX
Parameters118B
Benchmark date2026-08

Q4_K_M 118B MLX M5 Ultra

Setup Guide: Run Laguna S 2.1 on M5 Ultra

The recommended engine for Laguna S 2.1 on M5 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/laguna-s-21-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run laguna-s-21

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 26 tok/s 0.6s 128 GB MLX
M4 Max 24 tok/s 0.7s 128 GB MLX

System Requirements

To run Laguna S 2.1 on M5 Ultra you need:

🛒 Get a Mac that runs Laguna S 2.1

Laguna S 2.1 needs about 96 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 Laguna S 2.1 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard