The AI Bench
24 GB · 307 GB/s

What can the Mac mini (M5 Pro, 24 GB) run?

A quiet desk machine for models up to about 14B, and faster than the M6.

Best models for each task

Our top three for this machine. Chat and image tasks assume an 8K-token conversation; coding, documents and agents assume 32K.

Chat & writing18 of 25 run

  1. Gemma 4 12BRuns wellQ8_0 · needs 14.1 GB at 8K · 14–25tok/sSmooth
  2. Qwen3.8 27BRuns wellUD-IQ3_S · needs 14.5 GB at 8K · 14–25tok/sSmooth
  3. MiniCPM5 2BRuns greatQ8_0 · needs 4.0 GB at 8K · 55–95tok/sFast

Coding20 of 26 run

  1. Qwen3.8 27BFits with a tweakQ4_K_M · needs 21.5 GB at 32K · 9–15tok/sReadable
  2. Gemma 4 12BRuns wellQ8_0 · needs 14.7 GB at 32K · 13–20tok/sSmooth
  3. Qwen3.5 4BRuns greatQ8_0 · needs 7.2 GB at 32K · 30–55tok/sFast

Long documents13 of 20 run

  1. Qwen3.8 27BFits with a tweakQ4_K_M · needs 21.5 GB at 32K · 9–15tok/sReadable
  2. Gemma 4 12BRuns wellQ8_0 · needs 14.7 GB at 32K · 13–20tok/sSmooth
  3. Qwen3.5 9BRuns greatQ8_0 · needs 12.5 GB at 32K · 17–30tok/sSmooth

Agents & tools20 of 26 run

  1. Qwen3.8 27BFits with a tweakQ4_K_M · needs 21.5 GB at 32K · 9–15tok/sReadable
  2. Qwen3.5 4BRuns greatQ8_0 · needs 7.2 GB at 32K · 30–55tok/sFast
  3. Ornith 1.5 9BRuns greatQ8_0 · needs 11.9 GB at 32K · 16–25tok/sSmooth

Images in9 of 13 run

  1. Qwen3.8 27BRuns wellUD-IQ3_S · needs 14.5 GB at 8K · 14–25tok/sSmooth
  2. Gemma 4 12BRuns wellQ8_0 · needs 14.1 GB at 8K · 14–25tok/sSmooth
  3. Qwen3.5 9BRuns greatQ8_0 · needs 11.7 GB at 8K · 18–30tok/sSmooth

Make images6 of 6 run

  1. Stable Diffusion XL Base 1.0Runs greatFP16 · needs 7.9 GB
  2. FLUX.2 [klein] 4BRuns wellBF16 · needs 14.0 GB
  3. Z-Image-TurboRuns great4-bit GGUF · needs 5.0 GB

Speak text7 of 7 run

  1. Qwen3-TTS 1.7BRuns greatBF16 · needs 5.5 GB
  2. Kokoro-82MRuns greatFP32 · needs 1.4 GB
  3. Chatterbox Multilingual V3Runs greatFull · needs 4.2 GB

Transcribe7 of 7 run

  1. Whisper large-v3-turbo (via faster-whisper)Runs greatFP16 · needs 2.6 GB
  2. Nemotron 3.5 ASR Streaming 0.6BRuns greatFP32 · needs 3.5 GB
  3. Qwen3-ASR 1.7BRuns greatBF16 · needs 5.7 GB

Biggest model it runs well

Qwen3.8 27B (UD-IQ3_S, 12.0 GB file) at about 14–25tok/sSmooth.

Should you buy it?

Buy it if

You want a silent Mac for 8–14B models.

Skip it if

You want 27–35B models — you need 48 GB or more.

Watch out for

  • Memory cannot be upgraded later.

Measured on this hardware

Real runs from public sources, not estimates. All measurements.

ModelVersionPromptSpeedSource
Qwen3.8 27BUD-Q4_K_XL51213.4 tok/sOurs 2026-10-10
Qwen3.8 27BUD-Q4_K_XL32K10.28 tok/sOurs 2026-10-10