§01·compatibility · /check

Qwen3 32B on Apple M4 Max

✓ runsllmactiveapple series0GB VRAM

model

name: Qwen3 32B
slug: qwen3-32b
vertical: llm
status: active
repo: huggingface.co ↗

open detail ↗

gpu

name: Apple M4 Max
slug: m4-max
vram: 0 GB
series: apple

open detail ↗

§02·benchmarks

Task	Quant	Speed	VRAM	Works	Confidence	Source	Verified
llm	Q4	35tokens/s	20GB	✓		insiderllm.com· web	2026-05-15

§03·related recipes

llmintermediate29GB+
Qwen3-32B on RTX 5090: Q6_K_XL GGUF via llama.cpp (with AWQ-INT4 + 128K context alternative)
llmintermediate22GB+
Qwen3-32B on RTX 3090: UD-Q4_K_XL GGUF via llama.cpp
llmintermediate22GB+
Qwen3-32B on RTX 4090: UD-Q4_K_XL GGUF via llama.cpp