MacBook Pro M3 Max 36GB

macOS Ultra tier · Apple M3 Max · 36 GB RAM · 400 GB/s bandwidth
View device page →
BENCHMARK RESULTS (73)
Model Quant Measured Estimated RAM used App Source Date
Ternary Bonsai 8B Ternary Bonsai 8B Q2 223 tok/s 200 tok/s +12% 2.0 GB Ollama community 2026-01-15
Whisper Tiny Whisper Tiny FP16 217 tok/s 200 tok/s +9% 0.1 GB MacWhisper community 2026-01-18
Wav2Vec2 Base Wav2Vec2 Base FP16 216 tok/s 200 tok/s +8% 0.2 GB MacWhisper community 2026-04-09
SmolLM2 360M SmolLM2 360M FP16 215 tok/s 200 tok/s +8% 1.0 GB Xybrid CLI community 2026-01-05
🗣️ KittenTTS Nano FP16 215 tok/s 200 tok/s +8% 0.1 GB Piper community 2026-03-05
🗣️ OuteTTS 0.3 500M FP16 211 tok/s 200 tok/s +6% 1.1 GB Piper editorial 2026-01-17
🗣️ NeuTTS Air FP16 211 tok/s 200 tok/s +6% 1.8 GB Xybrid CLI community 2026-03-12
🎨 Stable Diffusion Turbo FP16 208 tok/s 190 tok/s +9% 2.7 GB Ollama editorial 2026-03-02
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 205 tok/s 200 tok/s +3% 1.5 GB Jan community 2026-05-24
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 204 tok/s 200 tok/s +2% 1.5 GB LM Studio editorial 2026-03-02
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 203 tok/s 200 tok/s +2% 0.5 GB Jan community 2026-04-20
🔢 GTE Large FP16 202 tok/s 200 tok/s +1% 0.8 GB Xybrid CLI community 2026-01-19
Ternary Bonsai 4B Ternary Bonsai 4B Q2 201 tok/s 200 tok/s +1% 1.0 GB Xybrid CLI editorial 2026-05-08
Bonsai Image 4B Bonsai Image 4B Q2 199 tok/s 200 tok/s +0% 2.2 GB Jan community 2026-05-26
Whisper Medium Whisper Medium FP16 197 tok/s 200 tok/s -1% 1.6 GB MacWhisper community 2026-01-28
🗣️ Kokoro 82M FP16 193 tok/s 200 tok/s -4% 0.4 GB Xybrid CLI community 2026-03-26
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 190 tok/s 200 tok/s -5% 2.0 GB Xybrid CLI community 2026-05-15
🔢 BGE Small FP16 190 tok/s 200 tok/s -5% 0.1 GB LM Studio community 2026-05-24
🗣️ KittenTTS Mini FP16 190 tok/s 200 tok/s -5% 0.2 GB Xybrid CLI community 2026-01-21
SmolLM2 135M SmolLM2 135M FP16 189 tok/s 200 tok/s -5% 0.3 GB Jan community 2026-02-24
Gemma 3 1B Gemma 3 1B FP16 189 tok/s 182 tok/s +4% 2.7 GB LM Studio community 2026-02-25
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 189 tok/s 200 tok/s -5% 1.3 GB Ollama community 2026-01-14
Whisper Small Whisper Small FP16 188 tok/s 200 tok/s -6% 0.5 GB MacWhisper community 2026-05-23
LFM2.5 1.2B LFM2.5 1.2B FP16 183 tok/s 171 tok/s +7% 2.5 GB Ollama community 2026-04-07
🔢 Nomic Embed Text FP16 179 tok/s 200 tok/s -10% 0.3 GB Jan community 2026-05-12
👁️ SmolVLM 500M FP16 178 tok/s 200 tok/s -11% 1.3 GB LM Studio editorial 2026-02-08
🔢 all-MiniLM-L6-v2 FP16 178 tok/s 200 tok/s -11% 0.1 GB Jan community 2026-04-06
🎙️ Distil-Whisper Large V3 FP16 178 tok/s 200 tok/s -11% 1.8 GB Xybrid CLI community 2026-05-23
TinyLlama 1.1B TinyLlama 1.1B FP16 172 tok/s 182 tok/s -5% 2.6 GB Jan community 2026-05-12
Llama 3.2 1B Llama 3.2 1B FP16 138 tok/s 148 tok/s -7% 3.4 GB LM Studio editorial 2026-01-03
Phi-4 Mini Phi-4 Mini Q5 135 tok/s 51 tok/s +165% 2.9 GB Ollama editorial 2026-03-20
Whisper Large V3 Whisper Large V3 FP16 132 tok/s 129 tok/s +2% 3.6 GB Xybrid CLI community 2026-02-08
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 124 tok/s 125 tok/s -1% 3.4 GB Xybrid CLI community 2026-04-07
🗣️ Dia 1.6B FP16 110 tok/s 121 tok/s -9% 4.1 GB Piper community 2026-05-25
StableLM 2 1.6B StableLM 2 1.6B FP16 108 tok/s 121 tok/s -11% 3.7 GB Jan community 2026-05-12
🧠 DeepSeek R1 Distill 1.5B FP16 108 tok/s 121 tok/s -11% 3.7 GB LM Studio editorial 2026-01-06
SmolLM2 1.7B SmolLM2 1.7B FP16 106 tok/s 118 tok/s -10% 3.8 GB LM Studio editorial 2026-02-07
Gemma 4 E2B Gemma 4 E2B FP16 99 tok/s 89 tok/s +11% 5.6 GB Ollama community 2026-01-18
👁️ Moondream 2B FP16 96 tok/s 108 tok/s -11% 4.6 GB Ollama community 2026-02-22
Mistral 7B Mistral 7B Q4 95 tok/s 27 tok/s +252% 4.3 GB LM Studio editorial 2026-03-20
🎨 Stable Diffusion 3.5 Medium FP16 94 tok/s 87 tok/s +8% 4.9 GB Xybrid CLI community 2026-05-27
Qwen 3.5 2B Qwen 3.5 2B FP16 93 tok/s 95 tok/s -2% 4.6 GB Ollama community 2026-02-08
Llama 3.2 3B Llama 3.2 3B FP16 68 tok/s 61 tok/s +11% 8.2 GB Xybrid CLI community 2026-04-21
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 68 tok/s 63 tok/s +8% 7.7 GB Jan community 2026-02-11
👨‍💻 StarCoder2 3B FP16 66 tok/s 65 tok/s +2% 7.1 GB LM Studio editorial 2026-04-04
Qwen 2.5 3B Qwen 2.5 3B FP16 65 tok/s 63 tok/s +3% 8.3 GB LM Studio editorial 2026-01-21
🎨 SDXL Turbo FP16 58 tok/s 62 tok/s -6% 8.1 GB Jan editorial 2026-02-17
Phi-4 Mini Phi-4 Mini FP16 56 tok/s 51 tok/s +10% 9.5 GB Ollama community 2026-02-22
Qwen 3.5 4B Qwen 3.5 4B FP16 53 tok/s 49 tok/s +8% 9.6 GB Jan community 2026-03-12
Gemma 4 E4B Gemma 4 E4B FP16 46 tok/s 44 tok/s +5% 10.3 GB LM Studio editorial 2026-01-14
Gemma 3 4B Gemma 3 4B FP16 44 tok/s 45 tok/s -2% 10.8 GB Jan community 2026-04-20
Gemma 3n E2B Gemma 3n E2B FP16 41 tok/s 45 tok/s -9% 11.4 GB LM Studio editorial 2026-04-22
👁️ LLaVA 1.6 7B FP16 30 tok/s 28 tok/s +7% 17.0 GB LM Studio community 2026-03-21
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 28 tok/s 25 tok/s +12% 17.9 GB LM Studio community 2026-02-10
🧠 DeepSeek R1 Distill 8B FP16 27 tok/s 25 tok/s +8% 17.4 GB LM Studio community 2026-01-05
👨‍💻 DeepSeek Coder 6.7B FP16 27 tok/s 29 tok/s -7% 16.6 GB Jan community 2026-01-17
Gemma 3n E4B Gemma 3n E4B FP16 26 tok/s 29 tok/s -10% 17.0 GB LM Studio community 2026-05-26
Llama 3.1 8B Llama 3.1 8B FP16 26 tok/s 25 tok/s +4% 19.0 GB Jan community 2026-03-14
LFM2.5 8B A1B LFM2.5 8B A1B FP16 26 tok/s 24 tok/s +8% 19.7 GB Xybrid CLI community 2026-03-17
Phi-4 Medium Phi-4 Medium Q8 25 tok/s 27 tok/s -7% 17.7 GB Ollama community 2026-03-13
Qwen 2.5 7B Qwen 2.5 7B FP16 24 tok/s 26 tok/s -8% 17.4 GB Ollama community 2026-01-08
Mistral 7B Mistral 7B FP16 24 tok/s 27 tok/s -11% 16.2 GB Ollama community 2026-03-05
🧠 Qwen3 8B FP16 24 tok/s 24 tok/s +0% 20.7 GB Jan community 2026-05-28
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 24 tok/s 26 tok/s -8% 16.4 GB LM Studio community 2026-01-01
🧠 DeepSeek R1 Distill 7B FP16 23 tok/s 26 tok/s -12% 19.5 GB Xybrid CLI editorial 2026-04-17
Qwen 3.5 9B Qwen 3.5 9B FP16 21 tok/s 22 tok/s -5% 20.0 GB Xybrid CLI community 2026-03-25
Gemma 4 26B A4B Gemma 4 26B A4B Q6 19 tok/s 19 tok/s +0% 26.0 GB LM Studio community 2026-03-28
Gemma 4 31B Gemma 4 31B Q6 19 tok/s 17 tok/s +12% 26.7 GB Ollama community 2026-04-10
Gemma 3 12B Gemma 3 12B FP16 18 tok/s 16 tok/s +13% 28.0 GB Jan community 2026-04-06
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q5 17 tok/s 17 tok/s +0% 31.0 GB Jan community 2026-05-27
Mistral Nemo 12B Mistral Nemo 12B FP16 16 tok/s 16 tok/s +0% 27.5 GB Ollama community 2026-02-11
👨‍💻 Laguna XS.2 Q6 15 tok/s 16 tok/s -6% 28.5 GB Jan community 2026-04-09
🎨 FLUX.1 Schnell FP16 15 tok/s 17 tok/s -12% 30.0 GB Xybrid CLI editorial 2026-04-17
← All benchmarks