MacBook Pro M2 Max 64GB

macOS Ultra tier · Apple M2 Max · 64 GB RAM · 400 GB/s bandwidth
View device page →
BENCHMARK RESULTS (75)
Model Quant Measured Estimated RAM used App Source Date
🔢 Nomic Embed Text FP16 224 tok/s 200 tok/s +12% 0.3 GB Ollama community 2026-04-10
🎙️ Distil-Whisper Large V3 FP16 224 tok/s 200 tok/s +12% 1.9 GB Xybrid CLI editorial 2026-04-22
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 217 tok/s 200 tok/s +9% 1.3 GB Xybrid CLI editorial 2026-01-03
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 215 tok/s 200 tok/s +8% 0.4 GB Xybrid CLI community 2026-05-27
Ternary Bonsai 8B Ternary Bonsai 8B Q2 213 tok/s 200 tok/s +7% 2.0 GB LM Studio community 2026-05-10
SmolLM2 360M SmolLM2 360M FP16 212 tok/s 200 tok/s +6% 1.2 GB Xybrid CLI community 2026-01-03
Whisper Tiny Whisper Tiny FP16 210 tok/s 200 tok/s +5% 0.1 GB MacWhisper editorial 2026-01-14
🗣️ KittenTTS Nano FP16 209 tok/s 200 tok/s +5% 0.1 GB Piper editorial 2026-03-01
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 208 tok/s 200 tok/s +4% 1.4 GB Jan community 2026-03-25
Wav2Vec2 Base Wav2Vec2 Base FP16 205 tok/s 200 tok/s +3% 0.3 GB MacWhisper editorial 2026-03-02
🗣️ Kokoro 82M FP16 202 tok/s 200 tok/s +1% 0.4 GB Xybrid CLI community 2026-04-03
🔢 BGE Small FP16 195 tok/s 200 tok/s -2% 0.1 GB Ollama community 2026-05-27
🗣️ OuteTTS 0.3 500M FP16 195 tok/s 200 tok/s -2% 1.1 GB Xybrid CLI community 2026-05-08
🔢 all-MiniLM-L6-v2 FP16 191 tok/s 200 tok/s -4% 0.1 GB Xybrid CLI community 2026-05-13
🗣️ KittenTTS Mini FP16 190 tok/s 200 tok/s -5% 0.2 GB Xybrid CLI community 2026-01-21
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 189 tok/s 200 tok/s -5% 1.4 GB Xybrid CLI community 2026-01-20
🔢 GTE Large FP16 188 tok/s 200 tok/s -6% 0.8 GB Jan community 2026-05-11
Bonsai Image 4B Bonsai Image 4B Q2 188 tok/s 200 tok/s -6% 2.2 GB Ollama community 2026-04-20
👁️ SmolVLM 500M FP16 186 tok/s 200 tok/s -7% 1.3 GB Ollama editorial 2026-03-13
Whisper Medium Whisper Medium FP16 185 tok/s 200 tok/s -7% 1.9 GB MacWhisper editorial 2026-04-21
SmolLM2 135M SmolLM2 135M FP16 183 tok/s 200 tok/s -8% 0.3 GB Jan community 2026-02-20
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 182 tok/s 200 tok/s -9% 2.0 GB Jan community 2026-05-11
TinyLlama 1.1B TinyLlama 1.1B FP16 181 tok/s 182 tok/s -1% 2.8 GB Xybrid CLI editorial 2026-01-17
Whisper Small Whisper Small FP16 180 tok/s 200 tok/s -10% 0.5 GB Xybrid CLI community 2026-04-18
Gemma 3 1B Gemma 3 1B FP16 177 tok/s 182 tok/s -3% 2.6 GB Xybrid CLI community 2026-01-18
🗣️ NeuTTS Air FP16 177 tok/s 200 tok/s -11% 1.8 GB Piper community 2026-04-20
Ternary Bonsai 4B Ternary Bonsai 4B Q2 176 tok/s 200 tok/s -12% 1.0 GB Ollama community 2026-02-22
🎨 Stable Diffusion Turbo FP16 175 tok/s 190 tok/s -8% 2.4 GB Jan community 2026-04-09
Llama 3.2 1B Llama 3.2 1B FP16 155 tok/s 148 tok/s +5% 3.2 GB Jan community 2026-03-17
LFM2.5 1.2B LFM2.5 1.2B FP16 154 tok/s 171 tok/s -10% 2.6 GB Jan community 2026-05-16
Whisper Large V3 Whisper Large V3 FP16 143 tok/s 129 tok/s +11% 3.7 GB Xybrid CLI community 2026-04-18
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 138 tok/s 125 tok/s +10% 4.0 GB Ollama community 2026-02-20
🗣️ Dia 1.6B FP16 133 tok/s 121 tok/s +10% 4.1 GB Xybrid CLI community 2026-04-20
🧠 DeepSeek R1 Distill 1.5B FP16 119 tok/s 121 tok/s -2% 4.1 GB Ollama community 2026-03-17
StableLM 2 1.6B StableLM 2 1.6B FP16 114 tok/s 121 tok/s -6% 4.0 GB Jan community 2026-01-18
SmolLM2 1.7B SmolLM2 1.7B FP16 112 tok/s 118 tok/s -5% 4.1 GB Ollama community 2026-03-13
Qwen 3.5 2B Qwen 3.5 2B FP16 100 tok/s 95 tok/s +5% 4.8 GB Jan community 2026-03-16
👁️ Moondream 2B FP16 97 tok/s 108 tok/s -10% 4.6 GB Jan community 2026-03-24
Mistral 7B Mistral 7B Q4 95 tok/s 27 tok/s +252% 4.3 GB LM Studio editorial 2026-03-19
Gemma 4 E2B Gemma 4 E2B FP16 90 tok/s 89 tok/s +1% 5.3 GB Ollama community 2026-04-15
🎨 Stable Diffusion 3.5 Medium FP16 87 tok/s 87 tok/s +0% 5.8 GB Jan community 2026-04-18
Phi-4 Mini Phi-4 Mini Q8 86 tok/s 51 tok/s +69% 4.6 GB Ollama editorial 2026-03-19
👨‍💻 StarCoder2 3B FP16 60 tok/s 65 tok/s -8% 7.7 GB Jan community 2026-02-20
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 60 tok/s 63 tok/s -5% 8.2 GB LM Studio editorial 2026-05-25
Qwen 2.5 3B Qwen 2.5 3B FP16 57 tok/s 63 tok/s -10% 7.2 GB Jan community 2026-04-07
Llama 3.2 3B Llama 3.2 3B FP16 55 tok/s 61 tok/s -10% 8.1 GB Xybrid CLI community 2026-05-24
🎨 SDXL Turbo FP16 55 tok/s 62 tok/s -11% 7.4 GB Ollama community 2026-04-10
Qwen 3.5 4B Qwen 3.5 4B FP16 52 tok/s 49 tok/s +6% 9.8 GB Jan community 2026-02-10
Phi-4 Mini Phi-4 Mini FP16 51 tok/s 51 tok/s +0% 8.4 GB Xybrid CLI community 2026-05-10
Gemma 3 4B Gemma 3 4B FP16 46 tok/s 45 tok/s +2% 10.7 GB Ollama community 2026-04-13
Gemma 3n E2B Gemma 3n E2B FP16 41 tok/s 45 tok/s -9% 9.6 GB LM Studio community 2026-05-23
Gemma 4 E4B Gemma 4 E4B FP16 40 tok/s 44 tok/s -9% 11.5 GB Jan community 2026-03-26
👨‍💻 DeepSeek Coder 6.7B FP16 31 tok/s 29 tok/s +7% 14.5 GB Ollama community 2026-04-05
Gemma 3n E4B Gemma 3n E4B FP16 27 tok/s 29 tok/s -7% 14.5 GB LM Studio community 2026-01-28
Mistral 7B Mistral 7B FP16 27 tok/s 27 tok/s +0% 18.4 GB Xybrid CLI editorial 2026-05-16
Qwen 2.5 7B Qwen 2.5 7B FP16 26 tok/s 26 tok/s +0% 18.9 GB Xybrid CLI community 2026-02-23
Llama 3.1 8B Llama 3.1 8B FP16 26 tok/s 25 tok/s +4% 18.4 GB Jan community 2026-03-14
🧠 DeepSeek R1 Distill 7B FP16 26 tok/s 26 tok/s +0% 16.6 GB Ollama community 2026-01-01
🧠 DeepSeek R1 Distill 8B FP16 25 tok/s 25 tok/s +0% 19.4 GB Jan community 2026-05-14
👁️ LLaVA 1.6 7B FP16 25 tok/s 28 tok/s -11% 18.5 GB Xybrid CLI editorial 2026-04-19
LFM2.5 8B A1B LFM2.5 8B A1B FP16 23 tok/s 24 tok/s -4% 17.9 GB Ollama community 2026-05-28
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 23 tok/s 26 tok/s -12% 18.9 GB Xybrid CLI community 2026-05-23
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 23 tok/s 25 tok/s -8% 19.2 GB LM Studio community 2026-03-15
Qwen 3.5 9B Qwen 3.5 9B FP16 22 tok/s 22 tok/s +0% 20.3 GB Xybrid CLI community 2026-04-04
🧠 Qwen3 8B FP16 22 tok/s 24 tok/s -8% 20.0 GB Ollama community 2026-04-19
🎨 FLUX.1 Schnell FP16 17 tok/s 17 tok/s +0% 25.6 GB Ollama community 2026-01-01
Gemma 3 12B Gemma 3 12B FP16 15 tok/s 16 tok/s -6% 28.1 GB Jan community 2026-04-11
Mistral Nemo 12B Mistral Nemo 12B FP16 15 tok/s 16 tok/s -6% 31.1 GB LM Studio editorial 2026-01-04
Gemma 4 26B A4B Gemma 4 26B A4B Q8 14 tok/s 14 tok/s +0% 35.4 GB LM Studio editorial 2026-02-27
Phi-4 Medium Phi-4 Medium FP16 14 tok/s 14 tok/s +0% 34.7 GB Jan community 2026-04-22
Gemma 4 31B Gemma 4 31B Q8 11 tok/s 12 tok/s -8% 36.9 GB Jan community 2026-05-15
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q8 11 tok/s 11 tok/s +0% 44.1 GB Ollama community 2026-04-20
👨‍💻 Laguna XS.2 Q8 10 tok/s 11 tok/s -9% 41.5 GB Jan community 2026-04-09
Qwen3 Coder Next Qwen3 Coder Next Q4 10 tok/s 9 tok/s +11% 56.3 GB Xybrid CLI community 2026-03-13
Llama 4 Scout Llama 4 Scout Q2 9 tok/s 10 tok/s -10% 49.7 GB LM Studio community 2026-03-21
← All benchmarks