MacBook Pro M5 Max 48GB

macOS Ultra tier · Apple M5 Max · 48 GB RAM · 600 GB/s bandwidth
View device page →
BENCHMARK RESULTS (72)
Model Quant Measured Estimated RAM used App Source Date
🎙️ Distil-Whisper Large V3 FP16 217 tok/s 200 tok/s +9% 1.7 GB Xybrid CLI editorial 2026-01-03
SmolLM2 360M SmolLM2 360M FP16 216 tok/s 200 tok/s +8% 1.0 GB Ollama community 2026-03-28
🔢 all-MiniLM-L6-v2 FP16 216 tok/s 200 tok/s +8% 0.1 GB Ollama community 2026-05-11
🗣️ Kokoro 82M FP16 216 tok/s 200 tok/s +8% 0.4 GB Xybrid CLI community 2026-04-17
Ternary Bonsai 8B Ternary Bonsai 8B Q2 215 tok/s 200 tok/s +8% 1.8 GB Ollama community 2026-04-08
🗣️ NeuTTS Air FP16 215 tok/s 200 tok/s +8% 1.6 GB Xybrid CLI community 2026-02-08
🔢 BGE Small FP16 214 tok/s 200 tok/s +7% 0.1 GB Ollama community 2026-02-19
Gemma 3 1B Gemma 3 1B FP16 212 tok/s 200 tok/s +6% 2.4 GB Xybrid CLI community 2026-01-03
🔢 GTE Large FP16 210 tok/s 200 tok/s +5% 0.9 GB Xybrid CLI community 2026-01-05
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 205 tok/s 200 tok/s +3% 1.6 GB Jan community 2026-01-02
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 202 tok/s 200 tok/s +1% 0.4 GB Jan community 2026-02-06
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 201 tok/s 200 tok/s +1% 1.4 GB LM Studio community 2026-04-05
LFM2.5 1.2B LFM2.5 1.2B FP16 201 tok/s 200 tok/s +1% 3.0 GB Jan community 2026-04-22
Wav2Vec2 Base Wav2Vec2 Base FP16 201 tok/s 200 tok/s +1% 0.2 GB Xybrid CLI community 2026-02-27
TinyLlama 1.1B TinyLlama 1.1B FP16 200 tok/s 200 tok/s +0% 2.8 GB Jan community 2026-04-18
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 200 tok/s 200 tok/s +0% 1.3 GB Ollama community 2026-01-02
Ternary Bonsai 4B Ternary Bonsai 4B Q2 200 tok/s 200 tok/s +0% 0.9 GB Ollama community 2026-01-05
Bonsai Image 4B Bonsai Image 4B Q2 199 tok/s 200 tok/s +0% 2.0 GB Ollama community 2026-01-01
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 198 tok/s 188 tok/s +5% 3.6 GB Jan community 2026-02-11
👁️ SmolVLM 500M FP16 197 tok/s 200 tok/s -1% 1.4 GB Xybrid CLI editorial 2026-02-25
Whisper Medium Whisper Medium FP16 194 tok/s 200 tok/s -3% 1.6 GB Xybrid CLI community 2026-04-04
🧠 DeepSeek R1 Distill 1.5B FP16 193 tok/s 182 tok/s +6% 3.9 GB Jan community 2026-02-09
SmolLM2 135M SmolLM2 135M FP16 192 tok/s 200 tok/s -4% 0.3 GB LM Studio community 2026-05-25
🗣️ KittenTTS Mini FP16 189 tok/s 200 tok/s -5% 0.2 GB Xybrid CLI community 2026-03-26
🗣️ OuteTTS 0.3 500M FP16 188 tok/s 200 tok/s -6% 1.1 GB Piper community 2026-05-23
🎨 Stable Diffusion Turbo FP16 187 tok/s 200 tok/s -6% 2.2 GB Jan community 2026-03-01
Whisper Small Whisper Small FP16 185 tok/s 200 tok/s -7% 0.6 GB MacWhisper editorial 2026-03-12
Whisper Large V3 Whisper Large V3 FP16 184 tok/s 194 tok/s -5% 4.0 GB Xybrid CLI community 2026-03-27
🔢 Nomic Embed Text FP16 182 tok/s 200 tok/s -9% 0.3 GB LM Studio editorial 2026-03-13
Llama 3.2 1B Llama 3.2 1B FP16 179 tok/s 200 tok/s -10% 3.1 GB LM Studio editorial 2026-02-09
🗣️ Dia 1.6B FP16 179 tok/s 182 tok/s -2% 4.0 GB Piper community 2026-04-22
Whisper Tiny Whisper Tiny FP16 178 tok/s 200 tok/s -11% 0.1 GB Xybrid CLI editorial 2026-05-23
SmolLM2 1.7B SmolLM2 1.7B FP16 177 tok/s 176 tok/s +1% 3.7 GB Ollama community 2026-02-09
🗣️ KittenTTS Nano FP16 177 tok/s 200 tok/s -11% 0.1 GB Xybrid CLI community 2026-02-20
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 176 tok/s 200 tok/s -12% 2.0 GB LM Studio community 2026-01-04
StableLM 2 1.6B StableLM 2 1.6B FP16 168 tok/s 182 tok/s -8% 3.8 GB LM Studio editorial 2026-03-15
👁️ Moondream 2B FP16 166 tok/s 162 tok/s +2% 4.8 GB LM Studio editorial 2026-01-21
Gemma 4 E2B Gemma 4 E2B FP16 138 tok/s 133 tok/s +4% 5.0 GB Jan community 2026-02-09
🎨 Stable Diffusion 3.5 Medium FP16 137 tok/s 130 tok/s +5% 4.9 GB Ollama community 2026-04-06
Qwen 3.5 2B Qwen 3.5 2B FP16 131 tok/s 143 tok/s -8% 5.4 GB Jan community 2026-02-20
👨‍💻 StarCoder2 3B FP16 108 tok/s 97 tok/s +11% 7.7 GB Xybrid CLI community 2026-05-24
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 98 tok/s 94 tok/s +4% 7.2 GB LM Studio editorial 2026-05-10
🎨 SDXL Turbo FP16 96 tok/s 92 tok/s +4% 7.6 GB LM Studio community 2026-04-07
Llama 3.2 3B Llama 3.2 3B FP16 89 tok/s 91 tok/s -2% 7.2 GB Xybrid CLI community 2026-03-27
Qwen 2.5 3B Qwen 2.5 3B FP16 86 tok/s 94 tok/s -9% 8.2 GB Jan community 2026-03-01
Gemma 3n E2B Gemma 3n E2B FP16 71 tok/s 67 tok/s +6% 11.5 GB Xybrid CLI community 2026-05-25
Phi-4 Mini Phi-4 Mini FP16 71 tok/s 77 tok/s -8% 10.0 GB LM Studio editorial 2026-04-20
Gemma 3 4B Gemma 3 4B FP16 70 tok/s 67 tok/s +4% 11.4 GB LM Studio editorial 2026-03-02
Qwen 3.5 4B Qwen 3.5 4B FP16 68 tok/s 73 tok/s -7% 10.6 GB Jan community 2026-04-02
Gemma 4 E4B Gemma 4 E4B FP16 63 tok/s 67 tok/s -6% 9.6 GB LM Studio community 2026-01-01
👨‍💻 DeepSeek Coder 6.7B FP16 48 tok/s 44 tok/s +9% 16.1 GB Ollama community 2026-01-15
🧠 DeepSeek R1 Distill 7B FP16 43 tok/s 39 tok/s +10% 18.6 GB Ollama community 2026-02-21
Mistral 7B Mistral 7B FP16 43 tok/s 41 tok/s +5% 17.4 GB LM Studio community 2026-05-08
Qwen 2.5 7B Qwen 2.5 7B FP16 41 tok/s 39 tok/s +5% 16.8 GB Xybrid CLI community 2026-05-01
Gemma 3n E4B Gemma 3n E4B FP16 40 tok/s 44 tok/s -9% 15.6 GB Ollama editorial 2026-03-17
🧠 Qwen3 8B FP16 39 tok/s 36 tok/s +8% 18.4 GB Ollama community 2026-03-03
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 39 tok/s 39 tok/s +0% 18.5 GB Jan community 2026-05-28
🧠 DeepSeek R1 Distill 8B FP16 38 tok/s 37 tok/s +3% 17.0 GB LM Studio community 2026-03-04
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 38 tok/s 37 tok/s +3% 18.5 GB Ollama community 2026-01-04
LFM2.5 8B A1B LFM2.5 8B A1B FP16 37 tok/s 36 tok/s +3% 21.5 GB Jan community 2026-05-24
👁️ LLaVA 1.6 7B FP16 37 tok/s 42 tok/s -12% 17.4 GB Ollama community 2026-01-17
Llama 3.1 8B Llama 3.1 8B FP16 33 tok/s 37 tok/s -11% 20.2 GB Ollama community 2026-01-17
Qwen 3.5 9B Qwen 3.5 9B FP16 29 tok/s 32 tok/s -9% 23.9 GB LM Studio editorial 2026-01-02
Gemma 3 12B Gemma 3 12B FP16 26 tok/s 24 tok/s +8% 27.3 GB Xybrid CLI community 2026-01-02
Mistral Nemo 12B Mistral Nemo 12B FP16 25 tok/s 24 tok/s +4% 28.7 GB LM Studio community 2026-01-16
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q6 24 tok/s 22 tok/s +9% 28.5 GB Ollama community 2026-02-27
🎨 FLUX.1 Schnell FP16 23 tok/s 25 tok/s -8% 25.1 GB Xybrid CLI community 2026-04-03
👨‍💻 Laguna XS.2 Q6 22 tok/s 24 tok/s -8% 28.7 GB LM Studio editorial 2026-02-09
Qwen3 Coder Next Qwen3 Coder Next Q2 22 tok/s 21 tok/s +5% 35.4 GB Jan community 2026-05-28
Phi-4 Medium Phi-4 Medium FP16 21 tok/s 21 tok/s +0% 34.6 GB Xybrid CLI community 2026-02-25
Gemma 4 26B A4B Gemma 4 26B A4B Q8 20 tok/s 21 tok/s -5% 36.4 GB Xybrid CLI community 2026-05-07
Gemma 4 31B Gemma 4 31B Q8 16 tok/s 18 tok/s -11% 42.0 GB Jan community 2026-02-22
← All benchmarks