Run Phi-5 Mini on M5 Max

Yes — Phi-5 Mini (4B) runs at 145 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.2s. A capable open-source LLM with 4B parameters.

Speed

145

tok/s

First Token

0.2

seconds

RAM Needed

128

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured Phi-5 Mini on M5 Max using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.

Metric	Value
Tokens per second	145 tok/s
Time to first token	0.2s
Quantization	Q4_K_M
Minimum RAM	128 GB
Recommended engine	MLX
Parameters	4B
Benchmark date	2026-05

Q4_K_M 4B MLX M5 Max

Setup Guide: Run Phi-5 Mini on M5 Max

The recommended engine for Phi-5 Mini on M5 Max is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/phi-5-mini-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run phi-5-mini

Performance on Other Apple Silicon Chips

Chip	Speed	First Token	Min RAM	Engine
M4 Pro	110 tok/s	0.3s	24 GB	Ollama
M5 Pro	95 tok/s	0.3s	24 GB	MLX
M3	88 tok/s	0.3s	16 GB	MLX
M2	68 tok/s	0.4s	8 GB	Ollama
M1	50 tok/s	0.5s	8 GB	Ollama

System Requirements

To run Phi-5 Mini on M5 Max you need:

• Mac with M5 Max chip (or newer)
• 128 GB unified memory minimum
• macOS 13 Ventura or later
• ~108-128 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

Compare More Models

See how Phi-5 Mini stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard