MacBook Pro M2 Pro 16GB

macOS High tier · Apple M2 Pro · 16 GB RAM · 200 GB/s bandwidth
View device page →
BENCHMARK RESULTS (72)
Model Quant Measured Estimated RAM used App Source Date
Whisper Small Whisper Small FP16 222 tok/s 200 tok/s +11% 0.6 GB Xybrid CLI community 2026-04-18
🗣️ Kokoro 82M FP16 221 tok/s 200 tok/s +11% 0.4 GB Piper community 2026-01-05
Ternary Bonsai 4B Ternary Bonsai 4B Q2 216 tok/s 200 tok/s +8% 1.0 GB Ollama community 2026-02-20
🗣️ KittenTTS Nano FP16 216 tok/s 200 tok/s +8% 0.1 GB Xybrid CLI community 2026-03-14
Whisper Tiny Whisper Tiny FP16 215 tok/s 200 tok/s +8% 0.1 GB MacWhisper community 2026-01-13
SmolLM2 135M SmolLM2 135M FP16 213 tok/s 200 tok/s +7% 0.3 GB Xybrid CLI community 2026-02-07
🗣️ KittenTTS Mini FP16 213 tok/s 200 tok/s +7% 0.2 GB Xybrid CLI community 2026-03-15
🔢 all-MiniLM-L6-v2 FP16 212 tok/s 200 tok/s +6% 0.1 GB Jan community 2026-04-18
SmolLM2 360M SmolLM2 360M FP16 207 tok/s 200 tok/s +4% 1.0 GB LM Studio editorial 2026-01-15
Wav2Vec2 Base Wav2Vec2 Base FP16 197 tok/s 200 tok/s -1% 0.3 GB Xybrid CLI community 2026-02-15
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 195 tok/s 200 tok/s -2% 0.5 GB Jan community 2026-04-18
🔢 Nomic Embed Text FP16 190 tok/s 200 tok/s -5% 0.3 GB Ollama editorial 2026-05-27
🗣️ OuteTTS 0.3 500M FP16 184 tok/s 200 tok/s -8% 1.2 GB Xybrid CLI community 2026-03-27
🔢 GTE Large FP16 183 tok/s 200 tok/s -8% 0.8 GB Jan community 2026-01-17
🔢 BGE Small FP16 177 tok/s 200 tok/s -11% 0.1 GB Jan community 2026-05-14
👁️ SmolVLM 500M FP16 168 tok/s 182 tok/s -8% 1.3 GB LM Studio community 2026-03-15
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 155 tok/s 172 tok/s -10% 1.4 GB LM Studio community 2026-02-07
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 149 tok/s 167 tok/s -11% 1.5 GB Xybrid CLI community 2026-04-17
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 148 tok/s 167 tok/s -11% 1.5 GB Xybrid CLI community 2026-05-23
🗣️ NeuTTS Air FP16 146 tok/s 133 tok/s +10% 1.8 GB Xybrid CLI community 2026-04-19
Whisper Medium Whisper Medium FP16 137 tok/s 133 tok/s +3% 1.7 GB Xybrid CLI community 2026-02-08
Ternary Bonsai 8B Ternary Bonsai 8B Q2 135 tok/s 125 tok/s +8% 1.9 GB Ollama community 2026-01-14
Gemma 3 1B Gemma 3 1B Q8 130 tok/s 91 tok/s +43% 1.5 GB Ollama editorial 2026-03-19
🎙️ Distil-Whisper Large V3 FP16 118 tok/s 133 tok/s -11% 1.9 GB MacWhisper editorial 2026-05-25
🎨 Stable Diffusion Turbo FP16 103 tok/s 95 tok/s +8% 2.2 GB Ollama community 2026-04-09
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 101 tok/s 111 tok/s -9% 2.3 GB LM Studio editorial 2026-04-20
Bonsai Image 4B Bonsai Image 4B Q2 99 tok/s 111 tok/s -11% 2.2 GB Ollama community 2026-01-17
TinyLlama 1.1B TinyLlama 1.1B FP16 92 tok/s 91 tok/s +1% 2.8 GB LM Studio editorial 2026-02-22
Gemma 3 1B Gemma 3 1B FP16 87 tok/s 91 tok/s -4% 2.6 GB Xybrid CLI community 2026-05-13
Phi-4 Mini Phi-4 Mini Q4 82 tok/s 26 tok/s +215% 2.4 GB LM Studio editorial 2026-03-19
LFM2.5 1.2B LFM2.5 1.2B FP16 82 tok/s 85 tok/s -4% 3.0 GB LM Studio editorial 2026-05-26
Whisper Large V3 Whisper Large V3 FP16 69 tok/s 65 tok/s +6% 4.0 GB MacWhisper editorial 2026-03-03
Llama 3.2 1B Llama 3.2 1B FP16 68 tok/s 74 tok/s -8% 3.4 GB LM Studio community 2026-04-20
StableLM 2 1.6B StableLM 2 1.6B FP16 67 tok/s 61 tok/s +10% 3.7 GB Jan community 2026-04-05
🧠 DeepSeek R1 Distill 1.5B FP16 65 tok/s 61 tok/s +7% 3.8 GB Ollama editorial 2026-01-13
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 64 tok/s 63 tok/s +2% 4.0 GB Jan community 2026-01-01
🗣️ Dia 1.6B FP16 60 tok/s 61 tok/s -2% 3.5 GB Piper community 2026-02-09
👁️ Moondream 2B FP16 56 tok/s 54 tok/s +4% 4.3 GB LM Studio community 2026-05-10
SmolLM2 1.7B SmolLM2 1.7B FP16 53 tok/s 59 tok/s -10% 3.8 GB Xybrid CLI editorial 2026-03-15
Qwen 3.5 2B Qwen 3.5 2B FP16 53 tok/s 48 tok/s +10% 4.8 GB Ollama community 2026-04-09
Gemma 4 E2B Gemma 4 E2B FP16 40 tok/s 44 tok/s -9% 5.1 GB LM Studio editorial 2026-03-13
🎨 Stable Diffusion 3.5 Medium FP16 38 tok/s 43 tok/s -12% 5.8 GB Jan community 2026-02-20
Qwen 2.5 3B Qwen 2.5 3B FP16 34 tok/s 31 tok/s +10% 7.6 GB Xybrid CLI community 2026-05-23
👨‍💻 StarCoder2 3B FP16 33 tok/s 32 tok/s +3% 6.5 GB Xybrid CLI community 2026-05-25
🎨 SDXL Turbo FP16 33 tok/s 31 tok/s +6% 6.9 GB Ollama community 2026-02-27
Llama 3.2 3B Llama 3.2 3B FP16 29 tok/s 30 tok/s -3% 7.3 GB Ollama community 2026-01-03
Gemma 3n E4B Gemma 3n E4B Q8 29 tok/s 27 tok/s +7% 8.9 GB Xybrid CLI community 2026-04-20
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 29 tok/s 31 tok/s -6% 6.8 GB Ollama community 2026-05-27
👨‍💻 DeepSeek Coder 6.7B Q8 28 tok/s 28 tok/s +0% 9.1 GB LM Studio editorial 2026-01-21
👁️ LLaVA 1.6 7B Q8 27 tok/s 27 tok/s +0% 9.6 GB LM Studio editorial 2026-02-26
Qwen 3.5 4B Qwen 3.5 4B FP16 26 tok/s 24 tok/s +8% 8.8 GB Ollama community 2026-03-04
Phi-4 Mini Phi-4 Mini FP16 26 tok/s 26 tok/s +0% 9.7 GB Ollama community 2026-04-22
🧠 DeepSeek R1 Distill 8B Q8 26 tok/s 24 tok/s +8% 10.1 GB Ollama community 2026-01-13
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q8 26 tok/s 24 tok/s +8% 9.4 GB Xybrid CLI editorial 2026-01-03
Qwen 2.5 7B Qwen 2.5 7B Q8 25 tok/s 25 tok/s +0% 8.7 GB Ollama community 2026-01-04
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q8 25 tok/s 25 tok/s +0% 9.1 GB Ollama community 2026-02-11
Llama 3.1 8B Llama 3.1 8B Q8 24 tok/s 24 tok/s +0% 9.5 GB Ollama community 2026-01-04
🧠 DeepSeek R1 Distill 7B Q8 23 tok/s 25 tok/s -8% 10.3 GB LM Studio editorial 2026-05-25
Mistral 7B Mistral 7B Q8 23 tok/s 24 tok/s -4% 9.0 GB Ollama community 2026-02-08
🧠 Qwen3 8B Q8 23 tok/s 23 tok/s +0% 10.0 GB LM Studio editorial 2026-05-10
Mistral Nemo 12B Mistral Nemo 12B Q6 22 tok/s 21 tok/s +5% 10.8 GB Ollama community 2026-02-11
Gemma 3n E2B Gemma 3n E2B FP16 21 tok/s 22 tok/s -5% 11.4 GB LM Studio editorial 2026-05-24
Gemma 3 12B Gemma 3 12B Q6 21 tok/s 21 tok/s +0% 10.8 GB Ollama community 2026-01-04
Gemma 4 E4B Gemma 4 E4B FP16 21 tok/s 22 tok/s -5% 10.8 GB Ollama community 2026-03-13
LFM2.5 8B A1B LFM2.5 8B A1B Q8 21 tok/s 23 tok/s -9% 9.9 GB Jan community 2026-04-06
🎨 FLUX.1 Schnell Q6 21 tok/s 22 tok/s -5% 12.0 GB Ollama editorial 2026-05-28
Gemma 3 4B Gemma 3 4B FP16 20 tok/s 22 tok/s -9% 11.1 GB Jan community 2026-05-20
Gemma 4 26B A4B Gemma 4 26B A4B Q2 20 tok/s 20 tok/s +0% 11.0 GB Ollama community 2026-05-28
👨‍💻 Laguna XS.2 Q2 20 tok/s 18 tok/s +11% 12.0 GB Jan community 2026-05-12
Gemma 4 31B Gemma 4 31B Q2 19 tok/s 19 tok/s +0% 13.1 GB Xybrid CLI editorial 2026-05-16
Qwen 3.5 9B Qwen 3.5 9B Q8 19 tok/s 21 tok/s -10% 12.1 GB Jan community 2026-02-23
Phi-4 Medium Phi-4 Medium Q6 19 tok/s 19 tok/s +0% 12.3 GB LM Studio editorial 2026-05-10
← All benchmarks