Mac Mini M4 16GB

macOS High tier · Apple M4 · 16 GB RAM · 120 GB/s bandwidth
View device page →
BENCHMARK RESULTS (72)
Model Quant Measured Estimated RAM used App Source Date
🗣️ Kokoro 82M FP16 224 tok/s 200 tok/s +12% 0.4 GB Xybrid CLI community 2026-04-22
Wav2Vec2 Base Wav2Vec2 Base FP16 218 tok/s 200 tok/s +9% 0.3 GB MacWhisper community 2026-02-10
Whisper Small Whisper Small FP16 216 tok/s 200 tok/s +8% 0.5 GB Xybrid CLI community 2026-01-02
🔢 BGE Small FP16 204 tok/s 200 tok/s +2% 0.1 GB LM Studio community 2026-01-13
Whisper Tiny Whisper Tiny FP16 204 tok/s 200 tok/s +2% 0.1 GB MacWhisper community 2026-02-10
SmolLM2 135M SmolLM2 135M FP16 199 tok/s 200 tok/s +0% 0.3 GB Ollama community 2026-01-02
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 197 tok/s 200 tok/s -1% 0.4 GB Jan community 2026-01-03
🗣️ KittenTTS Nano FP16 195 tok/s 200 tok/s -2% 0.1 GB Xybrid CLI community 2026-04-02
🔢 Nomic Embed Text FP16 191 tok/s 200 tok/s -4% 0.3 GB Ollama community 2026-04-19
🔢 all-MiniLM-L6-v2 FP16 189 tok/s 200 tok/s -5% 0.1 GB Jan community 2026-02-23
🗣️ KittenTTS Mini FP16 189 tok/s 200 tok/s -5% 0.2 GB Xybrid CLI community 2026-03-27
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 185 tok/s 100 tok/s +85% 0.9 GB Ollama editorial 2026-03-20
🔢 GTE Large FP16 182 tok/s 179 tok/s +2% 0.9 GB Jan community 2026-01-01
Ternary Bonsai 4B Ternary Bonsai 4B Q2 150 tok/s 140 tok/s +7% 1.0 GB Xybrid CLI community 2026-03-13
SmolLM2 360M SmolLM2 360M FP16 142 tok/s 130 tok/s +9% 1.0 GB Ollama community 2026-03-01
👁️ SmolVLM 500M FP16 120 tok/s 109 tok/s +10% 1.2 GB Jan community 2026-05-11
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 107 tok/s 100 tok/s +7% 1.6 GB Xybrid CLI community 2026-02-07
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 106 tok/s 103 tok/s +3% 1.3 GB Jan community 2026-02-06
🗣️ OuteTTS 0.3 500M FP16 106 tok/s 120 tok/s -12% 1.2 GB Xybrid CLI community 2026-03-17
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 89 tok/s 100 tok/s -11% 1.5 GB Jan community 2026-02-20
🎙️ Distil-Whisper Large V3 FP16 86 tok/s 80 tok/s +8% 1.6 GB Xybrid CLI community 2026-01-02
Ternary Bonsai 8B Ternary Bonsai 8B Q2 77 tok/s 75 tok/s +3% 2.0 GB LM Studio editorial 2026-03-03
Whisper Medium Whisper Medium FP16 77 tok/s 80 tok/s -4% 1.6 GB Xybrid CLI community 2026-04-04
🗣️ NeuTTS Air FP16 74 tok/s 80 tok/s -7% 1.8 GB Piper community 2026-04-19
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 71 tok/s 67 tok/s +6% 2.2 GB Xybrid CLI community 2026-05-25
Bonsai Image 4B Bonsai Image 4B Q2 71 tok/s 67 tok/s +6% 2.1 GB Jan community 2026-02-10
Phi-4 Mini Phi-4 Mini Q4 58 tok/s 15 tok/s +287% 2.4 GB LM Studio editorial 2026-03-20
🎨 Stable Diffusion Turbo FP16 56 tok/s 57 tok/s -2% 2.2 GB Xybrid CLI community 2026-04-07
TinyLlama 1.1B TinyLlama 1.1B FP16 53 tok/s 55 tok/s -4% 2.6 GB Ollama community 2026-03-13
Gemma 3 1B Gemma 3 1B FP16 52 tok/s 55 tok/s -5% 2.6 GB Ollama community 2026-04-18
LFM2.5 1.2B LFM2.5 1.2B FP16 52 tok/s 51 tok/s +2% 2.9 GB Jan community 2026-05-24
Llama 3.2 1B Llama 3.2 1B FP16 49 tok/s 44 tok/s +11% 2.9 GB LM Studio community 2026-01-06
SmolLM2 1.7B SmolLM2 1.7B FP16 36 tok/s 35 tok/s +3% 4.0 GB Jan community 2026-03-12
🗣️ Dia 1.6B FP16 35 tok/s 36 tok/s -3% 4.1 GB Piper community 2026-04-22
Whisper Large V3 Whisper Large V3 FP16 35 tok/s 39 tok/s -10% 4.0 GB Xybrid CLI community 2026-02-22
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 34 tok/s 38 tok/s -11% 4.0 GB LM Studio editorial 2026-04-20
👁️ Moondream 2B FP16 34 tok/s 32 tok/s +6% 4.8 GB LM Studio editorial 2026-02-26
🧠 DeepSeek R1 Distill 1.5B FP16 33 tok/s 36 tok/s -8% 4.1 GB LM Studio community 2026-04-20
StableLM 2 1.6B StableLM 2 1.6B FP16 32 tok/s 36 tok/s -11% 3.8 GB LM Studio editorial 2026-02-11
Qwen 3.5 2B Qwen 3.5 2B FP16 32 tok/s 29 tok/s +10% 5.1 GB Ollama community 2026-01-16
Gemma 4 E2B Gemma 4 E2B FP16 30 tok/s 27 tok/s +11% 5.5 GB Xybrid CLI community 2026-04-17
🎨 Stable Diffusion 3.5 Medium FP16 26 tok/s 26 tok/s +0% 6.0 GB LM Studio editorial 2026-04-26
Llama 3.2 3B Llama 3.2 3B FP16 20 tok/s 18 tok/s +11% 7.8 GB Ollama community 2026-01-13
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 19 tok/s 19 tok/s +0% 7.4 GB LM Studio editorial 2026-05-08
🎨 SDXL Turbo FP16 18 tok/s 18 tok/s +0% 7.0 GB Xybrid CLI community 2026-03-01
Qwen 2.5 3B Qwen 2.5 3B FP16 17 tok/s 19 tok/s -11% 7.8 GB Jan community 2026-03-26
🧠 DeepSeek R1 Distill 7B Q8 17 tok/s 15 tok/s +13% 10.1 GB Ollama community 2026-02-21
Mistral 7B Mistral 7B Q8 17 tok/s 15 tok/s +13% 10.6 GB Ollama community 2026-01-16
👨‍💻 StarCoder2 3B FP16 17 tok/s 19 tok/s -11% 7.5 GB Xybrid CLI community 2026-05-25
👁️ LLaVA 1.6 7B Q8 17 tok/s 16 tok/s +6% 8.7 GB LM Studio editorial 2026-04-06
Gemma 3n E4B Gemma 3n E4B Q8 16 tok/s 16 tok/s +0% 9.6 GB Jan community 2026-01-03
Qwen 2.5 7B Qwen 2.5 7B Q8 16 tok/s 15 tok/s +7% 10.5 GB Xybrid CLI community 2026-05-01
Llama 3.1 8B Llama 3.1 8B Q8 16 tok/s 14 tok/s +14% 10.2 GB Ollama community 2026-01-15
Phi-4 Mini Phi-4 Mini FP16 16 tok/s 15 tok/s +7% 9.0 GB Jan community 2026-02-10
🧠 Qwen3 8B Q8 16 tok/s 14 tok/s +14% 9.5 GB Jan community 2026-04-06
👨‍💻 DeepSeek Coder 6.7B Q8 16 tok/s 17 tok/s -6% 7.7 GB Xybrid CLI community 2026-03-28
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q8 16 tok/s 15 tok/s +7% 8.6 GB Xybrid CLI community 2026-02-08
Mistral Nemo 12B Mistral Nemo 12B Q6 15 tok/s 13 tok/s +15% 11.3 GB Jan community 2026-03-24
Qwen 3.5 4B Qwen 3.5 4B FP16 15 tok/s 15 tok/s +0% 10.6 GB Xybrid CLI community 2026-04-07
Gemma 3n E2B Gemma 3n E2B FP16 14 tok/s 13 tok/s +8% 9.7 GB Xybrid CLI community 2026-05-26
Gemma 3 12B Gemma 3 12B Q6 14 tok/s 13 tok/s +8% 12.2 GB Xybrid CLI community 2026-05-28
LFM2.5 8B A1B LFM2.5 8B A1B Q8 14 tok/s 14 tok/s +0% 10.7 GB Jan community 2026-04-20
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q8 14 tok/s 14 tok/s +0% 9.4 GB Ollama community 2026-01-05
Gemma 3 4B Gemma 3 4B FP16 13 tok/s 13 tok/s +0% 10.5 GB Xybrid CLI community 2026-02-24
Gemma 4 E4B Gemma 4 E4B FP16 13 tok/s 13 tok/s +0% 10.0 GB Ollama community 2026-02-11
Qwen 3.5 9B Qwen 3.5 9B Q8 13 tok/s 12 tok/s +8% 11.9 GB Jan community 2026-04-17
🧠 DeepSeek R1 Distill 8B Q8 13 tok/s 14 tok/s -7% 9.9 GB Xybrid CLI community 2026-01-20
Gemma 4 26B A4B Gemma 4 26B A4B Q2 11 tok/s 12 tok/s -8% 12.5 GB Jan community 2026-03-25
Gemma 4 31B Gemma 4 31B Q2 11 tok/s 11 tok/s +0% 11.3 GB LM Studio community 2026-04-04
Phi-4 Medium Phi-4 Medium Q6 11 tok/s 11 tok/s +0% 11.4 GB LM Studio community 2026-03-01
👨‍💻 Laguna XS.2 Q2 11 tok/s 11 tok/s +0% 13.9 GB Ollama community 2026-03-17
🎨 FLUX.1 Schnell Q6 11 tok/s 13 tok/s -15% 11.2 GB Jan community 2026-03-25
← All benchmarks