MacBook Pro M2 Pro 32GB

macOS Ultra tier · Apple M2 Pro · 32 GB RAM · 200 GB/s bandwidth
View device page →
BENCHMARK RESULTS (73)
Model Quant Measured Estimated RAM used App Source Date
Wav2Vec2 Base Wav2Vec2 Base FP16 221 tok/s 200 tok/s +11% 0.3 GB Xybrid CLI community 2026-04-17
SmolLM2 135M SmolLM2 135M FP16 218 tok/s 200 tok/s +9% 0.3 GB Ollama community 2026-02-19
🔢 all-MiniLM-L6-v2 FP16 218 tok/s 200 tok/s +9% 0.1 GB Ollama community 2026-04-07
🔢 BGE Small FP16 217 tok/s 200 tok/s +9% 0.1 GB Ollama community 2026-04-06
SmolLM2 360M SmolLM2 360M FP16 215 tok/s 200 tok/s +8% 1.1 GB Ollama community 2026-05-11
🔢 Nomic Embed Text FP16 211 tok/s 200 tok/s +6% 0.3 GB Jan community 2026-02-09
Ternary Bonsai 4B Ternary Bonsai 4B Q2 207 tok/s 200 tok/s +4% 1.0 GB LM Studio editorial 2026-04-06
🗣️ OuteTTS 0.3 500M FP16 206 tok/s 200 tok/s +3% 1.1 GB Piper editorial 2026-05-08
🔢 GTE Large FP16 202 tok/s 200 tok/s +1% 0.9 GB LM Studio editorial 2026-02-25
👁️ SmolVLM 500M FP16 199 tok/s 182 tok/s +9% 1.4 GB Ollama community 2026-02-22
Whisper Tiny Whisper Tiny FP16 196 tok/s 200 tok/s -2% 0.1 GB Xybrid CLI community 2026-03-28
🗣️ KittenTTS Mini FP16 192 tok/s 200 tok/s -4% 0.2 GB Xybrid CLI community 2026-01-16
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 189 tok/s 172 tok/s +10% 1.3 GB LM Studio community 2026-02-11
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 186 tok/s 200 tok/s -7% 0.5 GB LM Studio community 2026-03-16
🗣️ KittenTTS Nano FP16 183 tok/s 200 tok/s -8% 0.1 GB Xybrid CLI community 2026-04-08
Whisper Small Whisper Small FP16 182 tok/s 200 tok/s -9% 0.6 GB Xybrid CLI community 2026-05-13
🗣️ Kokoro 82M FP16 179 tok/s 200 tok/s -10% 0.4 GB Piper editorial 2026-02-12
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 160 tok/s 167 tok/s -4% 1.5 GB Xybrid CLI community 2026-05-16
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 148 tok/s 167 tok/s -11% 1.5 GB LM Studio editorial 2026-04-19
🎙️ Distil-Whisper Large V3 FP16 146 tok/s 133 tok/s +10% 1.8 GB Xybrid CLI community 2026-01-13
Whisper Medium Whisper Medium FP16 135 tok/s 133 tok/s +2% 1.7 GB MacWhisper community 2026-02-10
Ternary Bonsai 8B Ternary Bonsai 8B Q2 128 tok/s 125 tok/s +2% 1.8 GB LM Studio editorial 2026-05-11
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 123 tok/s 111 tok/s +11% 2.1 GB Xybrid CLI community 2026-05-23
🗣️ NeuTTS Air FP16 120 tok/s 133 tok/s -10% 1.9 GB Piper editorial 2026-05-27
Bonsai Image 4B Bonsai Image 4B Q2 101 tok/s 111 tok/s -9% 2.1 GB Ollama community 2026-02-11
TinyLlama 1.1B TinyLlama 1.1B FP16 96 tok/s 91 tok/s +5% 2.5 GB Jan community 2026-03-14
Gemma 3 1B Gemma 3 1B FP16 94 tok/s 91 tok/s +3% 2.8 GB LM Studio editorial 2026-03-03
LFM2.5 1.2B LFM2.5 1.2B FP16 90 tok/s 85 tok/s +6% 2.8 GB Jan community 2026-03-11
🎨 Stable Diffusion Turbo FP16 87 tok/s 95 tok/s -8% 2.6 GB LM Studio editorial 2026-05-26
Llama 3.2 1B Llama 3.2 1B FP16 79 tok/s 74 tok/s +7% 2.9 GB Ollama community 2026-03-28
Whisper Large V3 Whisper Large V3 FP16 72 tok/s 65 tok/s +11% 3.8 GB Xybrid CLI community 2026-05-24
Phi-4 Mini Phi-4 Mini Q5 68 tok/s 26 tok/s +162% 2.9 GB Ollama editorial 2026-03-19
🧠 DeepSeek R1 Distill 1.5B FP16 65 tok/s 61 tok/s +7% 4.0 GB LM Studio community 2026-01-16
StableLM 2 1.6B StableLM 2 1.6B FP16 61 tok/s 61 tok/s +0% 3.7 GB Ollama community 2026-01-01
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 60 tok/s 63 tok/s -5% 3.9 GB Ollama community 2026-03-13
🗣️ Dia 1.6B FP16 59 tok/s 61 tok/s -3% 4.1 GB Xybrid CLI community 2026-05-14
SmolLM2 1.7B SmolLM2 1.7B FP16 56 tok/s 59 tok/s -5% 4.3 GB Ollama community 2026-04-19
👁️ Moondream 2B FP16 52 tok/s 54 tok/s -4% 4.6 GB Ollama community 2026-03-14
Mistral 7B Mistral 7B Q4 48 tok/s 14 tok/s +243% 4.3 GB LM Studio editorial 2026-03-19
Qwen 3.5 2B Qwen 3.5 2B FP16 47 tok/s 48 tok/s -2% 5.2 GB Xybrid CLI community 2026-01-18
Gemma 4 E2B Gemma 4 E2B FP16 40 tok/s 44 tok/s -9% 5.1 GB LM Studio editorial 2026-03-16
🎨 Stable Diffusion 3.5 Medium FP16 39 tok/s 43 tok/s -9% 5.8 GB Jan community 2026-03-24
Llama 3.2 3B Llama 3.2 3B FP16 33 tok/s 30 tok/s +10% 7.1 GB Ollama community 2026-03-01
👨‍💻 StarCoder2 3B FP16 32 tok/s 32 tok/s +0% 7.0 GB Xybrid CLI editorial 2026-05-09
Qwen 2.5 3B Qwen 2.5 3B FP16 31 tok/s 31 tok/s +0% 7.9 GB LM Studio community 2026-02-26
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 30 tok/s 31 tok/s -3% 8.2 GB LM Studio editorial 2026-01-02
🎨 SDXL Turbo FP16 30 tok/s 31 tok/s -3% 7.3 GB LM Studio editorial 2026-05-25
Phi-4 Mini Phi-4 Mini FP16 24 tok/s 26 tok/s -8% 8.4 GB Jan community 2026-02-23
Gemma 3n E2B Gemma 3n E2B FP16 23 tok/s 22 tok/s +5% 10.5 GB Jan community 2026-04-17
Qwen 3.5 4B Qwen 3.5 4B FP16 23 tok/s 24 tok/s -4% 9.6 GB Jan community 2026-01-17
Gemma 4 E4B Gemma 4 E4B FP16 20 tok/s 22 tok/s -9% 10.1 GB LM Studio editorial 2026-02-07
Gemma 3 4B Gemma 3 4B FP16 19 tok/s 22 tok/s -14% 11.2 GB Jan community 2026-03-25
Mistral Nemo 12B Mistral Nemo 12B Q8 18 tok/s 16 tok/s +13% 15.3 GB Xybrid CLI community 2026-03-16
🎨 FLUX.1 Schnell Q8 16 tok/s 16 tok/s +0% 15.9 GB LM Studio editorial 2026-02-27
Gemma 3n E4B Gemma 3n E4B FP16 15 tok/s 15 tok/s +0% 14.8 GB Ollama community 2026-01-02
Gemma 3 12B Gemma 3 12B Q8 15 tok/s 15 tok/s +0% 14.6 GB Xybrid CLI community 2026-04-20
Mistral 7B Mistral 7B FP16 14 tok/s 14 tok/s +0% 16.9 GB Ollama community 2026-02-11
Phi-4 Medium Phi-4 Medium Q8 14 tok/s 14 tok/s +0% 17.7 GB Ollama community 2026-05-24
👁️ LLaVA 1.6 7B FP16 14 tok/s 14 tok/s +0% 15.3 GB Ollama community 2026-02-09
Llama 3.1 8B Llama 3.1 8B FP16 13 tok/s 12 tok/s +8% 18.1 GB Ollama community 2026-03-02
🧠 DeepSeek R1 Distill 8B FP16 13 tok/s 12 tok/s +8% 18.9 GB LM Studio community 2026-01-16
👨‍💻 DeepSeek Coder 6.7B FP16 13 tok/s 15 tok/s -13% 17.4 GB Xybrid CLI editorial 2026-04-18
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 13 tok/s 13 tok/s +0% 16.5 GB Ollama community 2026-05-28
Qwen 2.5 7B Qwen 2.5 7B FP16 12 tok/s 13 tok/s -8% 17.2 GB Ollama community 2026-03-05
🧠 DeepSeek R1 Distill 7B FP16 12 tok/s 13 tok/s -8% 19.3 GB LM Studio editorial 2026-05-26
🧠 Qwen3 8B FP16 12 tok/s 12 tok/s +0% 19.2 GB LM Studio editorial 2026-05-08
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 12 tok/s 12 tok/s +0% 20.5 GB Ollama community 2026-04-18
Qwen 3.5 9B Qwen 3.5 9B FP16 11 tok/s 11 tok/s +0% 19.7 GB Xybrid CLI community 2026-04-06
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q4 11 tok/s 10 tok/s +10% 25.7 GB Xybrid CLI community 2026-05-25
LFM2.5 8B A1B LFM2.5 8B A1B FP16 11 tok/s 12 tok/s -8% 20.4 GB LM Studio community 2026-05-27
Gemma 4 31B Gemma 4 31B Q5 10 tok/s 10 tok/s +0% 27.1 GB Ollama editorial 2026-01-28
👨‍💻 Laguna XS.2 Q5 10 tok/s 9 tok/s +11% 25.9 GB Xybrid CLI community 2026-04-19
Gemma 4 26B A4B Gemma 4 26B A4B Q6 9 tok/s 10 tok/s -10% 24.6 GB Jan community 2026-04-11
← All benchmarks