Mac Mini M4 Pro 24GB

macOS Ultra tier · Apple M4 Pro · 24 GB RAM · 273 GB/s bandwidth
View device page →
BENCHMARK RESULTS (73)
Model Quant Measured Estimated RAM used App Source Date
🗣️ KittenTTS Nano FP16 222 tok/s 200 tok/s +11% 0.1 GB Piper community 2026-02-12
SmolLM2 135M SmolLM2 135M FP16 220 tok/s 200 tok/s +10% 0.3 GB LM Studio editorial 2026-04-28
Ternary Bonsai 4B Ternary Bonsai 4B Q2 218 tok/s 200 tok/s +9% 1.0 GB Ollama community 2026-04-10
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 217 tok/s 200 tok/s +9% 1.5 GB Ollama community 2026-02-21
SmolLM2 360M SmolLM2 360M FP16 216 tok/s 200 tok/s +8% 1.0 GB Ollama community 2026-04-05
🔢 all-MiniLM-L6-v2 FP16 208 tok/s 200 tok/s +4% 0.1 GB LM Studio community 2026-05-22
🔢 BGE Small FP16 208 tok/s 200 tok/s +4% 0.1 GB LM Studio community 2026-05-10
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 204 tok/s 200 tok/s +2% 1.4 GB LM Studio editorial 2026-05-07
🔢 Nomic Embed Text FP16 200 tok/s 200 tok/s +0% 0.3 GB Xybrid CLI editorial 2026-04-02
🗣️ Kokoro 82M FP16 200 tok/s 200 tok/s +0% 0.4 GB Piper community 2026-01-02
Whisper Tiny Whisper Tiny FP16 200 tok/s 200 tok/s +0% 0.1 GB MacWhisper community 2026-01-02
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 198 tok/s 200 tok/s -1% 1.2 GB Ollama community 2026-02-07
🗣️ NeuTTS Air FP16 197 tok/s 182 tok/s +8% 1.8 GB Piper community 2026-01-15
Wav2Vec2 Base Wav2Vec2 Base FP16 195 tok/s 200 tok/s -2% 0.3 GB Xybrid CLI community 2026-04-02
🔢 GTE Large FP16 192 tok/s 200 tok/s -4% 0.9 GB Xybrid CLI community 2026-03-28
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 191 tok/s 200 tok/s -4% 0.4 GB Ollama community 2026-01-06
Whisper Small Whisper Small FP16 191 tok/s 200 tok/s -4% 0.5 GB Xybrid CLI community 2026-04-05
👁️ SmolVLM 500M FP16 190 tok/s 200 tok/s -5% 1.3 GB Xybrid CLI community 2026-05-15
🗣️ KittenTTS Mini FP16 190 tok/s 200 tok/s -5% 0.2 GB Piper community 2026-04-21
🗣️ OuteTTS 0.3 500M FP16 187 tok/s 200 tok/s -6% 1.2 GB Xybrid CLI community 2026-01-17
Ternary Bonsai 8B Ternary Bonsai 8B Q2 185 tok/s 171 tok/s +8% 1.9 GB Xybrid CLI community 2026-03-15
🎙️ Distil-Whisper Large V3 FP16 172 tok/s 182 tok/s -5% 1.6 GB Xybrid CLI community 2026-04-04
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 169 tok/s 152 tok/s +11% 2.2 GB Ollama community 2026-02-21
Whisper Medium Whisper Medium FP16 168 tok/s 182 tok/s -8% 1.8 GB MacWhisper community 2026-02-09
Bonsai Image 4B Bonsai Image 4B Q2 146 tok/s 152 tok/s -4% 2.1 GB Ollama community 2026-01-11
Gemma 3 1B Gemma 3 1B FP16 133 tok/s 124 tok/s +7% 2.7 GB LM Studio community 2026-05-10
🎨 Stable Diffusion Turbo FP16 122 tok/s 130 tok/s -6% 2.6 GB Jan community 2026-02-23
LFM2.5 1.2B LFM2.5 1.2B FP16 121 tok/s 117 tok/s +3% 3.0 GB Xybrid CLI community 2026-01-03
TinyLlama 1.1B TinyLlama 1.1B FP16 121 tok/s 124 tok/s -2% 2.4 GB Xybrid CLI community 2026-04-05
Phi-4 Mini Phi-4 Mini Q5 105 tok/s 35 tok/s +200% 2.9 GB Ollama editorial 2026-03-20
Llama 3.2 1B Llama 3.2 1B FP16 92 tok/s 101 tok/s -9% 3.2 GB LM Studio community 2026-03-16
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 90 tok/s 85 tok/s +6% 3.6 GB Jan community 2026-04-17
🗣️ Dia 1.6B FP16 89 tok/s 83 tok/s +7% 4.0 GB Piper community 2026-05-10
StableLM 2 1.6B StableLM 2 1.6B FP16 87 tok/s 83 tok/s +5% 3.9 GB LM Studio community 2026-05-07
🧠 DeepSeek R1 Distill 1.5B FP16 86 tok/s 83 tok/s +4% 3.5 GB LM Studio community 2026-03-01
SmolLM2 1.7B SmolLM2 1.7B FP16 84 tok/s 80 tok/s +5% 3.7 GB LM Studio community 2026-02-25
Whisper Large V3 Whisper Large V3 FP16 80 tok/s 88 tok/s -9% 3.8 GB Xybrid CLI community 2026-03-28
👁️ Moondream 2B FP16 75 tok/s 74 tok/s +1% 4.8 GB LM Studio editorial 2026-02-26
Mistral 7B Mistral 7B Q4 71 tok/s 19 tok/s +274% 4.3 GB LM Studio editorial 2026-03-20
Gemma 4 E2B Gemma 4 E2B FP16 68 tok/s 61 tok/s +11% 5.0 GB Jan community 2026-05-13
Qwen 3.5 2B Qwen 3.5 2B FP16 61 tok/s 65 tok/s -6% 4.4 GB Jan community 2026-03-28
🎨 Stable Diffusion 3.5 Medium FP16 61 tok/s 59 tok/s +3% 5.8 GB LM Studio editorial 2026-02-24
👨‍💻 StarCoder2 3B FP16 49 tok/s 44 tok/s +11% 6.7 GB Ollama community 2026-04-05
Llama 3.2 3B Llama 3.2 3B FP16 44 tok/s 41 tok/s +7% 7.4 GB LM Studio editorial 2026-01-16
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 42 tok/s 43 tok/s -2% 6.8 GB Xybrid CLI community 2026-05-08
🎨 SDXL Turbo FP16 42 tok/s 42 tok/s +0% 7.3 GB Xybrid CLI editorial 2026-05-09
Qwen 2.5 3B Qwen 2.5 3B FP16 38 tok/s 43 tok/s -12% 7.1 GB LM Studio community 2026-02-07
Gemma 4 E4B Gemma 4 E4B FP16 33 tok/s 30 tok/s +10% 10.0 GB Ollama community 2026-03-28
Phi-4 Mini Phi-4 Mini FP16 33 tok/s 35 tok/s -6% 9.4 GB Jan community 2026-01-16
Gemma 3 4B Gemma 3 4B FP16 30 tok/s 31 tok/s -3% 10.5 GB Xybrid CLI community 2026-05-13
Qwen 3.5 4B Qwen 3.5 4B FP16 30 tok/s 33 tok/s -9% 10.1 GB Jan community 2026-02-21
Gemma 3n E2B Gemma 3n E2B FP16 29 tok/s 31 tok/s -6% 10.4 GB Ollama community 2026-03-17
Qwen 3.5 9B Qwen 3.5 9B Q8 26 tok/s 28 tok/s -7% 11.2 GB Xybrid CLI community 2026-05-13
🎨 FLUX.1 Schnell Q8 23 tok/s 21 tok/s +10% 15.6 GB Ollama community 2026-01-16
Mistral Nemo 12B Mistral Nemo 12B Q8 22 tok/s 21 tok/s +5% 14.4 GB LM Studio editorial 2026-05-09
👨‍💻 Laguna XS.2 Q3 22 tok/s 20 tok/s +10% 17.4 GB Ollama community 2026-02-22
Gemma 3 12B Gemma 3 12B Q8 21 tok/s 21 tok/s +0% 14.3 GB LM Studio community 2026-05-12
Gemma 4 31B Gemma 4 31B Q3 21 tok/s 20 tok/s +5% 15.5 GB Ollama editorial 2026-02-18
Gemma 3n E4B Gemma 3n E4B FP16 19 tok/s 20 tok/s -5% 16.9 GB Ollama community 2026-03-18
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q3 19 tok/s 18 tok/s +6% 17.6 GB Jan community 2026-03-14
🧠 DeepSeek R1 Distill 7B FP16 19 tok/s 18 tok/s +6% 20.1 GB Xybrid CLI community 2026-05-26
👨‍💻 DeepSeek Coder 6.7B FP16 19 tok/s 20 tok/s -5% 14.4 GB Xybrid CLI community 2026-05-07
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 19 tok/s 18 tok/s +6% 16.3 GB Xybrid CLI community 2026-01-02
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 19 tok/s 17 tok/s +12% 18.1 GB Ollama community 2026-04-07
Gemma 4 26B A4B Gemma 4 26B A4B Q4 18 tok/s 17 tok/s +6% 18.3 GB Ollama editorial 2026-05-12
Mistral 7B Mistral 7B FP16 18 tok/s 19 tok/s -5% 17.3 GB Ollama community 2026-04-18
Phi-4 Medium Phi-4 Medium Q8 18 tok/s 18 tok/s +0% 16.9 GB Ollama community 2026-01-04
👁️ LLaVA 1.6 7B FP16 18 tok/s 19 tok/s -5% 15.2 GB Jan community 2026-03-01
Qwen 2.5 7B Qwen 2.5 7B FP16 17 tok/s 18 tok/s -6% 19.8 GB Xybrid CLI community 2026-04-05
Llama 3.1 8B Llama 3.1 8B FP16 17 tok/s 17 tok/s +0% 19.2 GB LM Studio community 2026-05-20
LFM2.5 8B A1B LFM2.5 8B A1B FP16 16 tok/s 16 tok/s +0% 20.7 GB Jan community 2026-05-01
🧠 DeepSeek R1 Distill 8B FP16 15 tok/s 17 tok/s -12% 18.7 GB Jan community 2026-04-10
🧠 Qwen3 8B FP16 15 tok/s 16 tok/s -6% 20.3 GB Xybrid CLI community 2026-01-21
← All benchmarks