MacBook Pro M1 Pro 32GB

macOS Ultra tier · Apple M1 Pro · 32 GB RAM · 200 GB/s bandwidth
View device page →
BENCHMARK RESULTS (73)
Model Quant Measured Estimated RAM used App Source Date
SmolLM2 135M SmolLM2 135M FP16 224 tok/s 200 tok/s +12% 0.3 GB Xybrid CLI editorial 2026-04-19
🔢 Nomic Embed Text FP16 224 tok/s 200 tok/s +12% 0.3 GB Jan community 2026-03-25
SmolLM2 360M SmolLM2 360M FP16 218 tok/s 200 tok/s +9% 1.0 GB Ollama community 2026-04-10
🗣️ KittenTTS Mini FP16 215 tok/s 200 tok/s +8% 0.2 GB Xybrid CLI community 2026-01-05
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 213 tok/s 200 tok/s +7% 0.4 GB LM Studio community 2026-02-26
🗣️ Kokoro 82M FP16 207 tok/s 200 tok/s +4% 0.4 GB Xybrid CLI community 2026-02-09
Whisper Small Whisper Small FP16 200 tok/s 200 tok/s +0% 0.5 GB Xybrid CLI editorial 2026-04-02
Whisper Tiny Whisper Tiny FP16 198 tok/s 200 tok/s -1% 0.1 GB MacWhisper community 2026-02-10
Wav2Vec2 Base Wav2Vec2 Base FP16 195 tok/s 200 tok/s -2% 0.2 GB Xybrid CLI community 2026-03-27
🔢 BGE Small FP16 192 tok/s 200 tok/s -4% 0.1 GB Ollama community 2026-03-14
🔢 GTE Large FP16 190 tok/s 200 tok/s -5% 0.8 GB Ollama community 2026-03-13
🔢 all-MiniLM-L6-v2 FP16 188 tok/s 200 tok/s -6% 0.1 GB Xybrid CLI community 2026-03-26
🗣️ OuteTTS 0.3 500M FP16 186 tok/s 200 tok/s -7% 1.2 GB Xybrid CLI community 2026-05-13
🗣️ KittenTTS Nano FP16 184 tok/s 200 tok/s -8% 0.1 GB Xybrid CLI community 2026-03-26
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 178 tok/s 167 tok/s +7% 1.6 GB Xybrid CLI community 2026-01-04
Ternary Bonsai 4B Ternary Bonsai 4B Q2 177 tok/s 200 tok/s -11% 1.0 GB Ollama community 2026-03-05
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 169 tok/s 167 tok/s +1% 1.3 GB Xybrid CLI community 2026-05-09
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 167 tok/s 172 tok/s -3% 1.4 GB Xybrid CLI community 2026-01-18
👁️ SmolVLM 500M FP16 165 tok/s 182 tok/s -9% 1.4 GB Xybrid CLI editorial 2026-05-25
🎙️ Distil-Whisper Large V3 FP16 145 tok/s 133 tok/s +9% 1.6 GB Xybrid CLI community 2026-05-28
Whisper Medium Whisper Medium FP16 140 tok/s 133 tok/s +5% 1.8 GB Xybrid CLI community 2026-05-11
Ternary Bonsai 8B Ternary Bonsai 8B Q2 138 tok/s 125 tok/s +10% 1.9 GB Xybrid CLI community 2026-04-20
🗣️ NeuTTS Air FP16 120 tok/s 133 tok/s -10% 1.8 GB Xybrid CLI community 2026-03-25
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 109 tok/s 111 tok/s -2% 1.9 GB Xybrid CLI community 2026-04-02
Bonsai Image 4B Bonsai Image 4B Q2 109 tok/s 111 tok/s -2% 1.9 GB Ollama community 2026-02-09
TinyLlama 1.1B TinyLlama 1.1B FP16 96 tok/s 91 tok/s +5% 2.6 GB Jan community 2026-03-27
Gemma 3 1B Gemma 3 1B FP16 91 tok/s 91 tok/s +0% 2.6 GB Ollama editorial 2026-05-19
🎨 Stable Diffusion Turbo FP16 84 tok/s 95 tok/s -12% 2.3 GB LM Studio editorial 2026-03-14
Llama 3.2 1B Llama 3.2 1B FP16 78 tok/s 74 tok/s +5% 3.1 GB LM Studio editorial 2026-05-08
LFM2.5 1.2B LFM2.5 1.2B FP16 76 tok/s 85 tok/s -11% 2.7 GB LM Studio editorial 2026-01-06
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 70 tok/s 63 tok/s +11% 3.6 GB Ollama community 2026-03-02
Phi-4 Mini Phi-4 Mini Q5 68 tok/s 26 tok/s +162% 2.9 GB Ollama editorial 2026-03-15
🧠 DeepSeek R1 Distill 1.5B FP16 65 tok/s 61 tok/s +7% 3.9 GB Xybrid CLI community 2026-04-19
🗣️ Dia 1.6B FP16 64 tok/s 61 tok/s +5% 3.7 GB Piper editorial 2026-05-10
👁️ Moondream 2B FP16 59 tok/s 54 tok/s +9% 4.4 GB Xybrid CLI community 2026-03-16
Whisper Large V3 Whisper Large V3 FP16 59 tok/s 65 tok/s -9% 3.5 GB MacWhisper editorial 2026-02-08
SmolLM2 1.7B SmolLM2 1.7B FP16 58 tok/s 59 tok/s -2% 3.8 GB Ollama community 2026-02-09
StableLM 2 1.6B StableLM 2 1.6B FP16 56 tok/s 61 tok/s -8% 3.7 GB Ollama editorial 2026-04-18
Qwen 3.5 2B Qwen 3.5 2B FP16 51 tok/s 48 tok/s +6% 4.5 GB Xybrid CLI community 2026-05-27
Mistral 7B Mistral 7B Q4 48 tok/s 14 tok/s +243% 4.3 GB LM Studio editorial 2026-03-15
Gemma 4 E2B Gemma 4 E2B FP16 41 tok/s 44 tok/s -7% 5.7 GB LM Studio editorial 2026-04-22
🎨 Stable Diffusion 3.5 Medium FP16 40 tok/s 43 tok/s -7% 5.5 GB Jan community 2026-05-15
Qwen 2.5 3B Qwen 2.5 3B FP16 32 tok/s 31 tok/s +3% 8.2 GB Jan community 2026-04-21
🎨 SDXL Turbo FP16 31 tok/s 31 tok/s +0% 7.0 GB LM Studio community 2026-04-04
👨‍💻 StarCoder2 3B FP16 30 tok/s 32 tok/s -6% 7.4 GB Jan community 2026-05-16
Llama 3.2 3B Llama 3.2 3B FP16 29 tok/s 30 tok/s -3% 7.9 GB Jan community 2026-04-19
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 29 tok/s 31 tok/s -6% 8.1 GB Jan community 2026-02-22
Phi-4 Mini Phi-4 Mini FP16 26 tok/s 26 tok/s +0% 8.3 GB Ollama community 2026-01-03
Qwen 3.5 4B Qwen 3.5 4B FP16 25 tok/s 24 tok/s +4% 10.3 GB Jan community 2026-05-27
Gemma 3 4B Gemma 3 4B FP16 23 tok/s 22 tok/s +5% 11.6 GB LM Studio editorial 2026-03-03
Gemma 4 E4B Gemma 4 E4B FP16 23 tok/s 22 tok/s +5% 10.7 GB Xybrid CLI community 2026-04-18
Gemma 3n E2B Gemma 3n E2B FP16 22 tok/s 22 tok/s +0% 9.8 GB Xybrid CLI community 2026-04-02
Mistral Nemo 12B Mistral Nemo 12B Q8 17 tok/s 16 tok/s +6% 15.3 GB LM Studio community 2026-05-09
👨‍💻 DeepSeek Coder 6.7B FP16 16 tok/s 15 tok/s +7% 16.8 GB Ollama community 2026-02-19
🎨 FLUX.1 Schnell Q8 16 tok/s 16 tok/s +0% 14.3 GB Xybrid CLI editorial 2026-05-08
Gemma 3 12B Gemma 3 12B Q8 15 tok/s 15 tok/s +0% 15.5 GB Ollama community 2026-04-21
Mistral 7B Mistral 7B FP16 15 tok/s 14 tok/s +7% 16.5 GB LM Studio editorial 2026-05-09
Gemma 3n E4B Gemma 3n E4B FP16 14 tok/s 15 tok/s -7% 17.2 GB Jan community 2026-03-27
Phi-4 Medium Phi-4 Medium Q8 14 tok/s 14 tok/s +0% 18.6 GB LM Studio editorial 2026-01-20
Llama 3.1 8B Llama 3.1 8B FP16 13 tok/s 12 tok/s +8% 17.3 GB LM Studio community 2026-01-04
👁️ LLaVA 1.6 7B FP16 13 tok/s 14 tok/s -7% 16.8 GB Ollama community 2026-04-21
Qwen 2.5 7B Qwen 2.5 7B FP16 12 tok/s 13 tok/s -8% 16.3 GB Jan community 2026-03-28
LFM2.5 8B A1B LFM2.5 8B A1B FP16 12 tok/s 12 tok/s +0% 18.4 GB LM Studio editorial 2026-05-11
🧠 DeepSeek R1 Distill 7B FP16 12 tok/s 13 tok/s -8% 18.2 GB LM Studio community 2026-02-10
🧠 Qwen3 8B FP16 12 tok/s 12 tok/s +0% 19.4 GB Jan community 2026-03-12
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 12 tok/s 13 tok/s -8% 16.6 GB LM Studio community 2026-02-11
Qwen 3.5 9B Qwen 3.5 9B FP16 11 tok/s 11 tok/s +0% 20.4 GB Ollama community 2026-02-10
🧠 DeepSeek R1 Distill 8B FP16 11 tok/s 12 tok/s -8% 20.6 GB LM Studio editorial 2026-05-24
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 11 tok/s 12 tok/s -8% 20.7 GB LM Studio editorial 2026-04-22
Gemma 4 31B Gemma 4 31B Q5 10 tok/s 10 tok/s +0% 25.1 GB LM Studio community 2026-01-06
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q4 10 tok/s 10 tok/s +0% 25.9 GB Ollama editorial 2026-02-07
Gemma 4 26B A4B Gemma 4 26B A4B Q6 9 tok/s 10 tok/s -10% 26.4 GB Jan community 2026-03-27
👨‍💻 Laguna XS.2 Q5 8 tok/s 9 tok/s -11% 26.5 GB Ollama community 2026-03-14
← All benchmarks