Run Laguna XS 2.1 on M4 Pro

Yes — Laguna XS 2.1 (33B-A3B) runs at 25 tok/s on M4 Pro with 24 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.4s. A capable open-source LLM with 33B-A3B parameters.

Speed
25
tok/s
First Token
0.4
seconds
RAM Needed
24
GB minimum
Engine
Ollama
recommended
Want to run Laguna XS 2.1 faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Laguna XS 2.1 on M4 Pro 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 second25 tok/s
Time to first token0.4s
QuantizationQ4_K_M
Minimum RAM24 GB
Recommended engineOllama
Parameters33B-A3B
Benchmark date2026-08

Q4_K_M 33B-A3B Ollama M4 Pro

Setup Guide: Run Laguna XS 2.1 on M4 Pro

The recommended engine for Laguna XS 2.1 on M4 Pro is Ollama. Install Ollama, then pull the model:

ollama run laguna-xs-21

Ollama handles quantization automatically — it will download the Q4_K_M variant (~24 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 55 tok/s 0.3s 64 GB MLX

System Requirements

To run Laguna XS 2.1 on M4 Pro you need:

🛒 Get a Mac that runs Laguna XS 2.1

Laguna XS 2.1 needs about 24 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 XS 2.1 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard