MacBook Pro M1 Max 32GB

macOS Ultra tier · Apple M1 Max · 32 GB RAM · 400 GB/s bandwidth
View device page →
BENCHMARK RESULTS (73)
Model Quant Measured Estimated RAM used App Source Date
Bonsai Image 4B Bonsai Image 4B Q2 219 tok/s 200 tok/s +10% 2.0 GB Xybrid CLI editorial 2026-02-07
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 218 tok/s 200 tok/s +9% 1.3 GB Ollama community 2026-03-01
Whisper Medium Whisper Medium FP16 218 tok/s 200 tok/s +9% 1.8 GB Xybrid CLI community 2026-04-21
🗣️ OuteTTS 0.3 500M FP16 216 tok/s 200 tok/s +8% 1.2 GB Piper community 2026-05-11
🔢 BGE Small FP16 215 tok/s 200 tok/s +8% 0.1 GB Ollama community 2026-03-02
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 213 tok/s 200 tok/s +7% 2.3 GB LM Studio editorial 2026-03-03
🗣️ KittenTTS Mini FP16 212 tok/s 200 tok/s +6% 0.2 GB Xybrid CLI community 2026-02-09
🗣️ Kokoro 82M FP16 210 tok/s 200 tok/s +5% 0.4 GB Piper community 2026-01-17
SmolLM2 135M SmolLM2 135M FP16 208 tok/s 200 tok/s +4% 0.3 GB Jan community 2026-05-10
🗣️ KittenTTS Nano FP16 206 tok/s 200 tok/s +3% 0.1 GB Piper editorial 2026-03-02
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 203 tok/s 200 tok/s +2% 1.4 GB Jan community 2026-05-26
SmolLM2 360M SmolLM2 360M FP16 199 tok/s 200 tok/s +0% 1.1 GB Jan community 2026-04-20
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 199 tok/s 200 tok/s +0% 0.5 GB Jan community 2026-05-26
Whisper Tiny Whisper Tiny FP16 199 tok/s 200 tok/s +0% 0.1 GB Xybrid CLI community 2026-05-26
🔢 GTE Large FP16 198 tok/s 200 tok/s -1% 0.7 GB Ollama community 2026-01-04
Wav2Vec2 Base Wav2Vec2 Base FP16 198 tok/s 200 tok/s -1% 0.3 GB Xybrid CLI community 2026-01-17
Ternary Bonsai 4B Ternary Bonsai 4B Q2 197 tok/s 200 tok/s -1% 0.9 GB Xybrid CLI community 2026-04-03
Gemma 3 1B Gemma 3 1B FP16 193 tok/s 182 tok/s +6% 2.8 GB LM Studio editorial 2026-03-03
👁️ SmolVLM 500M FP16 188 tok/s 200 tok/s -6% 1.3 GB Ollama community 2026-02-11
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 187 tok/s 200 tok/s -6% 1.3 GB LM Studio community 2026-01-28
TinyLlama 1.1B TinyLlama 1.1B FP16 185 tok/s 182 tok/s +2% 2.5 GB Jan community 2026-03-13
Ternary Bonsai 8B Ternary Bonsai 8B Q2 182 tok/s 200 tok/s -9% 2.0 GB Jan community 2026-03-28
Whisper Small Whisper Small FP16 179 tok/s 200 tok/s -10% 0.5 GB Xybrid CLI community 2026-05-15
🗣️ NeuTTS Air FP16 178 tok/s 200 tok/s -11% 1.7 GB Xybrid CLI community 2026-04-05
🎙️ Distil-Whisper Large V3 FP16 178 tok/s 200 tok/s -11% 1.8 GB MacWhisper community 2026-04-20
🔢 all-MiniLM-L6-v2 FP16 177 tok/s 200 tok/s -11% 0.1 GB Jan community 2026-04-08
🔢 Nomic Embed Text FP16 177 tok/s 200 tok/s -11% 0.3 GB LM Studio editorial 2026-05-25
🎨 Stable Diffusion Turbo FP16 169 tok/s 190 tok/s -11% 2.3 GB Jan community 2026-04-08
LFM2.5 1.2B LFM2.5 1.2B FP16 161 tok/s 171 tok/s -6% 2.5 GB LM Studio community 2026-01-01
Phi-4 Mini Phi-4 Mini Q5 135 tok/s 51 tok/s +165% 2.9 GB Ollama editorial 2026-03-15
Llama 3.2 1B Llama 3.2 1B FP16 135 tok/s 148 tok/s -9% 3.5 GB LM Studio editorial 2026-05-25
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 128 tok/s 125 tok/s +2% 3.7 GB LM Studio editorial 2026-05-08
🗣️ Dia 1.6B FP16 128 tok/s 121 tok/s +6% 3.6 GB Piper community 2026-03-28
SmolLM2 1.7B SmolLM2 1.7B FP16 126 tok/s 118 tok/s +7% 3.9 GB Ollama editorial 2026-01-13
Whisper Large V3 Whisper Large V3 FP16 119 tok/s 129 tok/s -8% 4.0 GB MacWhisper editorial 2026-04-21
StableLM 2 1.6B StableLM 2 1.6B FP16 117 tok/s 121 tok/s -3% 3.8 GB Jan community 2026-02-23
🧠 DeepSeek R1 Distill 1.5B FP16 113 tok/s 121 tok/s -7% 3.8 GB LM Studio community 2026-04-20
👁️ Moondream 2B FP16 106 tok/s 108 tok/s -2% 4.1 GB Xybrid CLI community 2026-05-08
Qwen 3.5 2B Qwen 3.5 2B FP16 102 tok/s 95 tok/s +7% 5.0 GB Jan community 2026-02-10
Mistral 7B Mistral 7B Q4 95 tok/s 27 tok/s +252% 4.3 GB LM Studio editorial 2026-03-15
Gemma 4 E2B Gemma 4 E2B FP16 90 tok/s 89 tok/s +1% 5.6 GB Jan community 2026-04-20
🎨 Stable Diffusion 3.5 Medium FP16 88 tok/s 87 tok/s +1% 5.9 GB Jan community 2026-05-01
🎨 SDXL Turbo FP16 69 tok/s 62 tok/s +11% 7.4 GB Jan community 2026-05-12
Llama 3.2 3B Llama 3.2 3B FP16 64 tok/s 61 tok/s +5% 7.4 GB Jan community 2026-03-16
Qwen 2.5 3B Qwen 2.5 3B FP16 63 tok/s 63 tok/s +0% 8.1 GB LM Studio editorial 2026-01-21
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 63 tok/s 63 tok/s +0% 7.2 GB Jan community 2026-03-11
👨‍💻 StarCoder2 3B FP16 60 tok/s 65 tok/s -8% 7.1 GB Ollama editorial 2026-03-17
Qwen 3.5 4B Qwen 3.5 4B FP16 54 tok/s 49 tok/s +10% 9.8 GB Xybrid CLI community 2026-05-23
Phi-4 Mini Phi-4 Mini FP16 54 tok/s 51 tok/s +6% 8.5 GB Xybrid CLI community 2026-05-26
Gemma 4 E4B Gemma 4 E4B FP16 49 tok/s 44 tok/s +11% 10.6 GB LM Studio community 2026-04-12
Gemma 3n E2B Gemma 3n E2B FP16 46 tok/s 45 tok/s +2% 10.3 GB Ollama community 2026-02-11
Gemma 3 4B Gemma 3 4B FP16 45 tok/s 45 tok/s +0% 10.6 GB Jan community 2026-05-25
Gemma 3 12B Gemma 3 12B Q8 32 tok/s 31 tok/s +3% 13.7 GB LM Studio community 2026-03-28
🎨 FLUX.1 Schnell Q8 31 tok/s 31 tok/s +0% 15.7 GB LM Studio community 2026-03-28
Phi-4 Medium Phi-4 Medium Q8 30 tok/s 27 tok/s +11% 16.1 GB Xybrid CLI community 2026-01-03
Mistral Nemo 12B Mistral Nemo 12B Q8 29 tok/s 31 tok/s -6% 13.6 GB LM Studio community 2026-04-22
👁️ LLaVA 1.6 7B FP16 29 tok/s 28 tok/s +4% 16.1 GB Jan community 2026-02-07
Mistral 7B Mistral 7B FP16 28 tok/s 27 tok/s +4% 16.7 GB Jan community 2026-02-11
🧠 DeepSeek R1 Distill 7B FP16 27 tok/s 26 tok/s +4% 18.0 GB Jan community 2026-03-15
🧠 DeepSeek R1 Distill 8B FP16 27 tok/s 25 tok/s +8% 17.0 GB Xybrid CLI community 2026-01-05
👨‍💻 DeepSeek Coder 6.7B FP16 27 tok/s 29 tok/s -7% 15.2 GB Xybrid CLI community 2026-01-18
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 27 tok/s 25 tok/s +8% 19.2 GB Ollama community 2026-02-22
Gemma 3n E4B Gemma 3n E4B FP16 26 tok/s 29 tok/s -10% 16.6 GB Xybrid CLI community 2026-04-19
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 24 tok/s 26 tok/s -8% 19.9 GB LM Studio editorial 2026-05-23
Qwen 2.5 7B Qwen 2.5 7B FP16 23 tok/s 26 tok/s -12% 17.9 GB Jan community 2026-02-14
LFM2.5 8B A1B LFM2.5 8B A1B FP16 23 tok/s 24 tok/s -4% 20.2 GB Xybrid CLI community 2026-01-18
🧠 Qwen3 8B FP16 23 tok/s 24 tok/s -4% 20.1 GB Ollama community 2026-02-11
Llama 3.1 8B Llama 3.1 8B FP16 22 tok/s 25 tok/s -12% 19.5 GB Xybrid CLI community 2026-05-25
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q4 22 tok/s 20 tok/s +10% 21.8 GB LM Studio community 2026-01-06
Qwen 3.5 9B Qwen 3.5 9B FP16 21 tok/s 22 tok/s -5% 23.4 GB Xybrid CLI community 2026-04-03
Gemma 4 26B A4B Gemma 4 26B A4B Q6 19 tok/s 19 tok/s +0% 25.7 GB Xybrid CLI community 2026-02-24
👨‍💻 Laguna XS.2 Q5 18 tok/s 18 tok/s +0% 26.7 GB LM Studio community 2026-01-20
Gemma 4 31B Gemma 4 31B Q5 17 tok/s 19 tok/s -11% 24.6 GB Jan community 2026-05-13
← All benchmarks