Local AI hardware: M4 Pro

Hardware profile
Hardware	Memory	Bandwidth	Computing power	vLLM
M4 ProApple M4 Pro with 24 GB unified memory	24 GBUnified RAM	273 GB/s	not available	no

Compatible models Estimated speeds, not benchmark results: calculated from memory bandwidth and model size. Real results can differ significantly because there is no precise formula for deriving LLM generation speed from hardware specifications alone.
Model	Size	Approx. Q4 memory	Estimated generation
Ornith 1.0 35BMoE	35Bactive 3B	21 GB	58 tok/s4-bit quantization
Ornith 1.5 35BMoE	35Bactive 3B	21 GB	58 tok/s4-bit quantization
Qwen 3.6 35BMoE	35Bactive 3B	21 GB	58 tok/s4-bit quantization
Laguna XS 2.1MoE	33Bactive 3B	19.8 GB	58 tok/s4-bit quantization
Qwen 2.5 32BDense	32.5B	19.5 GB	7 tok/s4-bit quantization
Gemma 4 31BDense	31B	18.6 GB	8 tok/s4-bit quantization
Qwen 3 Coder 30BMoE	30.5Bactive 3.3B	18.3 GB	53 tok/s4-bit quantization
Granite 4.1 30BDense	30B	18 GB	8 tok/s4-bit quantization
Granite 4.2 30BDense	30B	18 GB	8 tok/s4-bit quantization
Muse GlimmerDense	30B	18 GB	8 tok/s4-bit quantization
GLM 4.7 FlashMoE	30Bactive 3B	18 GB	58 tok/s4-bit quantization
Nemotron 3.5 LightningMoE	30Bactive 3B	18 GB	58 tok/s4-bit quantization
Fara 1.5 27BDense	27B	16.2 GB	9 tok/s4-bit quantization
Qwen 3.6 27BDense	27B	16.2 GB	9 tok/s4-bit quantization
Qwen 3.8 27BDense	27B	16.2 GB	9 tok/s4-bit quantization
Gemma 4 26BMoE	26Bactive 4B	15.6 GB	44 tok/s4-bit quantization
GPT-OSS 20BMoE	20.9Bactive 3.6B	12.5 GB	49 tok/s4-bit quantization
Instella-MoE 16B ThinkMoE	16Bactive 2.8B	9.6 GB	61 tok/s4-bit quantization
Qwen 3 14BDense	14B	8.4 GB	17 tok/s4-bit quantization
Gemma 3 12BDense	12B	7.2 GB	20 tok/s4-bit quantization
Gemma 4 12BDense	12B	7.2 GB	20 tok/s4-bit quantization
Fara 1.5 9BDense	9B	5.4 GB	27 tok/s4-bit quantization
Ornith 1.0 9BDense	9B	5.4 GB	27 tok/s4-bit quantization
Ornith 1.5 9BDense	9B	5.4 GB	27 tok/s4-bit quantization
Qwen 3.5 9BDense	9B	5.4 GB	27 tok/s4-bit quantization
Qwythos 9BDense	9B	5.4 GB	27 tok/s4-bit quantization
Granite 4.1 8BDense	8B	4.8 GB	30 tok/s4-bit quantization
Granite 4.2 8BDense	8B	4.8 GB	30 tok/s4-bit quantization
Qwen 3 8BDense	8B	4.8 GB	30 tok/s4-bit quantization
Ling 3.0 TinyMoE	7.9Bactive 1.3B	4.7 GB	120 tok/s4-bit quantization
Fara 1.5 4BDense	4B	2.4 GB	59 tok/s4-bit quantization
Gemma 3 4BDense	4B	2.4 GB	59 tok/s4-bit quantization
Qwen 3 4B Instruct 2507Dense	4B	2.4 GB	59 tok/s4-bit quantization
Qwen 3.5 4BDense	4B	2.4 GB	59 tok/s4-bit quantization
Spark X2.5 4BDense	4B	2.4 GB	59 tok/s4-bit quantization
Granite 4.1 3BDense	3B	1.8 GB	78 tok/s4-bit quantization
Granite 4.2 3BDense	3B	1.8 GB	78 tok/s4-bit quantization
Llama 3.2 3B InstructDense	3B	1.8 GB	78 tok/s4-bit quantization
Ministral 3 3BDense	3B	1.8 GB	78 tok/s4-bit quantization
Nanbeige 4.2 3BDense	3B	1.8 GB	78 tok/s4-bit quantization

2 videos found Showing 1-2

Video Zero to MVP 2026-08-21

Ornith 1.5 Speed on a MacBook M4 Pro — 9B and 35B

Speed benchmarks for Ornith 1.5 9B dense and 35B MoE models running on a MacBook M4 Pro with 24 GB unified memory.

Testing Ornith 1.5 9B Ornith 1.5 35B M4 Pro

Video Zero to MVP 2026-07-29

Gemma 4 12B Coder Tested: Where Small Local Models Break

Tests Gemma 4 12B Coder locally on MacBook M4 Pro using Ollama and Pi agent via color palette generator, pixel art editor single prompts, and step-by-step development across 18 tasks.

Testing Gemma 4 12B M4 Pro