MacBook Pro M5 16GB

macOS High tier · Apple M5 · 16 GB RAM · 153 GB/s bandwidth
View device page →
BENCHMARK RESULTS (70)
Model Quant Measured Estimated RAM used App Source Date
Whisper Tiny Whisper Tiny FP16 223 tok/s 200 tok/s +12% 0.1 GB Xybrid CLI community 2026-04-23
Whisper Small Whisper Small FP16 221 tok/s 200 tok/s +11% 0.6 GB Xybrid CLI community 2026-04-20
🔢 BGE Small FP16 220 tok/s 200 tok/s +10% 0.1 GB Xybrid CLI community 2026-04-20
🔢 GTE Large FP16 208 tok/s 200 tok/s +4% 0.8 GB Jan community 2026-03-13
🗣️ KittenTTS Nano FP16 207 tok/s 200 tok/s +4% 0.1 GB Xybrid CLI community 2026-02-06
SmolLM2 135M SmolLM2 135M FP16 201 tok/s 200 tok/s +1% 0.3 GB Jan community 2026-05-24
🔢 all-MiniLM-L6-v2 FP16 200 tok/s 200 tok/s +0% 0.1 GB Ollama community 2026-02-08
🔢 Nomic Embed Text FP16 194 tok/s 200 tok/s -3% 0.3 GB Xybrid CLI community 2026-05-15
🗣️ KittenTTS Mini FP16 191 tok/s 200 tok/s -4% 0.2 GB Piper editorial 2026-05-28
🗣️ Kokoro 82M FP16 190 tok/s 200 tok/s -5% 0.4 GB Xybrid CLI editorial 2026-04-02
SmolLM2 360M SmolLM2 360M FP16 185 tok/s 166 tok/s +11% 1.0 GB LM Studio community 2026-01-04
Wav2Vec2 Base Wav2Vec2 Base FP16 182 tok/s 200 tok/s -9% 0.3 GB Xybrid CLI community 2026-05-11
Ternary Bonsai 4B Ternary Bonsai 4B Q2 179 tok/s 178 tok/s +1% 1.1 GB Jan community 2026-04-19
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 178 tok/s 200 tok/s -11% 0.5 GB Ollama community 2026-02-23
🗣️ OuteTTS 0.3 500M FP16 152 tok/s 153 tok/s -1% 1.3 GB Xybrid CLI community 2026-04-20
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 143 tok/s 132 tok/s +8% 1.4 GB Ollama community 2026-02-20
👁️ SmolVLM 500M FP16 142 tok/s 139 tok/s +2% 1.4 GB Jan community 2026-01-02
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 117 tok/s 128 tok/s -9% 1.4 GB Jan community 2026-05-12
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 117 tok/s 128 tok/s -9% 1.5 GB LM Studio editorial 2026-03-23
Whisper Medium Whisper Medium FP16 113 tok/s 102 tok/s +11% 1.7 GB MacWhisper community 2026-04-09
🗣️ NeuTTS Air FP16 106 tok/s 102 tok/s +4% 1.9 GB Piper editorial 2026-03-04
🎙️ Distil-Whisper Large V3 FP16 103 tok/s 102 tok/s +1% 1.9 GB Xybrid CLI community 2026-01-19
Bonsai Image 4B Bonsai Image 4B Q2 95 tok/s 85 tok/s +12% 2.2 GB Jan community 2026-02-19
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 92 tok/s 85 tok/s +8% 2.0 GB Ollama community 2026-04-08
Ternary Bonsai 8B Ternary Bonsai 8B Q2 91 tok/s 96 tok/s -5% 1.9 GB Ollama community 2026-04-18
Gemma 3 1B Gemma 3 1B FP16 78 tok/s 70 tok/s +11% 2.7 GB Xybrid CLI community 2026-05-24
🎨 Stable Diffusion Turbo FP16 70 tok/s 73 tok/s -4% 2.5 GB Xybrid CLI community 2026-01-19
TinyLlama 1.1B TinyLlama 1.1B FP16 65 tok/s 70 tok/s -7% 2.5 GB Jan community 2026-05-15
LFM2.5 1.2B LFM2.5 1.2B FP16 61 tok/s 65 tok/s -6% 2.8 GB Xybrid CLI community 2026-05-13
Llama 3.2 1B Llama 3.2 1B FP16 59 tok/s 57 tok/s +4% 3.3 GB Jan community 2026-02-10
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 54 tok/s 48 tok/s +13% 3.8 GB Ollama community 2026-01-15
Whisper Large V3 Whisper Large V3 FP16 50 tok/s 49 tok/s +2% 3.8 GB Xybrid CLI community 2026-03-01
StableLM 2 1.6B StableLM 2 1.6B FP16 49 tok/s 46 tok/s +7% 4.3 GB LM Studio editorial 2026-02-25
🧠 DeepSeek R1 Distill 1.5B FP16 48 tok/s 46 tok/s +4% 3.5 GB Jan community 2026-01-02
🗣️ Dia 1.6B FP16 47 tok/s 46 tok/s +2% 3.7 GB Piper community 2026-01-03
👁️ Moondream 2B FP16 43 tok/s 41 tok/s +5% 4.1 GB LM Studio editorial 2026-04-06
SmolLM2 1.7B SmolLM2 1.7B FP16 42 tok/s 45 tok/s -7% 4.3 GB Jan community 2026-03-01
Qwen 3.5 2B Qwen 3.5 2B FP16 40 tok/s 36 tok/s +11% 5.2 GB Xybrid CLI editorial 2026-04-19
🎨 Stable Diffusion 3.5 Medium FP16 35 tok/s 33 tok/s +6% 5.9 GB Xybrid CLI community 2026-01-03
Gemma 4 E2B Gemma 4 E2B FP16 34 tok/s 34 tok/s +0% 4.9 GB LM Studio community 2026-05-10
Qwen 2.5 3B Qwen 2.5 3B FP16 27 tok/s 24 tok/s +13% 8.2 GB Xybrid CLI editorial 2026-04-02
👨‍💻 StarCoder2 3B FP16 25 tok/s 25 tok/s +0% 7.7 GB Jan community 2026-05-26
Llama 3.2 3B Llama 3.2 3B FP16 24 tok/s 23 tok/s +4% 7.8 GB Jan community 2026-02-09
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 24 tok/s 24 tok/s +0% 8.0 GB Xybrid CLI editorial 2026-01-22
🎨 SDXL Turbo FP16 22 tok/s 24 tok/s -8% 7.3 GB Jan community 2026-04-07
Gemma 3n E4B Gemma 3n E4B Q8 21 tok/s 21 tok/s +0% 9.1 GB Xybrid CLI editorial 2026-05-16
Llama 3.1 8B Llama 3.1 8B Q8 20 tok/s 18 tok/s +11% 10.4 GB Xybrid CLI community 2026-03-13
Phi-4 Mini Phi-4 Mini FP16 20 tok/s 20 tok/s +0% 9.6 GB Jan community 2026-04-21
Mistral 7B Mistral 7B Q8 20 tok/s 19 tok/s +5% 10.4 GB Ollama editorial 2026-03-05
👨‍💻 DeepSeek Coder 6.7B Q8 20 tok/s 21 tok/s -5% 8.9 GB Xybrid CLI community 2026-05-14
Qwen 2.5 7B Qwen 2.5 7B Q8 19 tok/s 19 tok/s +0% 8.6 GB Ollama community 2026-05-28
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q8 19 tok/s 19 tok/s +0% 10.3 GB Xybrid CLI editorial 2026-01-19
👁️ LLaVA 1.6 7B Q8 19 tok/s 20 tok/s -5% 8.7 GB Xybrid CLI community 2026-01-19
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q8 19 tok/s 18 tok/s +6% 9.7 GB LM Studio editorial 2026-05-08
Gemma 3n E2B Gemma 3n E2B FP16 18 tok/s 17 tok/s +6% 11.3 GB LM Studio editorial 2026-03-04
Gemma 3 4B Gemma 3 4B FP16 18 tok/s 17 tok/s +6% 9.7 GB Xybrid CLI community 2026-02-07
🧠 DeepSeek R1 Distill 8B Q8 18 tok/s 18 tok/s +0% 10.8 GB Jan community 2026-05-28
🧠 Qwen3 8B Q8 18 tok/s 18 tok/s +0% 10.6 GB Jan community 2026-04-20
Gemma 3 12B Gemma 3 12B Q6 17 tok/s 16 tok/s +6% 10.0 GB Ollama community 2026-04-08
Qwen 3.5 4B Qwen 3.5 4B FP16 17 tok/s 19 tok/s -11% 9.9 GB Xybrid CLI community 2026-04-22
🧠 DeepSeek R1 Distill 7B Q8 17 tok/s 19 tok/s -11% 9.5 GB Jan community 2026-05-13
Gemma 4 31B Gemma 4 31B Q2 16 tok/s 15 tok/s +7% 11.1 GB LM Studio community 2026-02-26
Qwen 3.5 9B Qwen 3.5 9B Q8 16 tok/s 16 tok/s +0% 11.6 GB Ollama community 2026-04-21
LFM2.5 8B A1B LFM2.5 8B A1B Q8 16 tok/s 17 tok/s -6% 10.8 GB Xybrid CLI community 2026-02-23
Mistral Nemo 12B Mistral Nemo 12B Q6 15 tok/s 16 tok/s -6% 11.0 GB Xybrid CLI community 2026-05-15
Gemma 4 E4B Gemma 4 E4B FP16 15 tok/s 17 tok/s -12% 11.1 GB Jan community 2026-05-19
Gemma 4 26B A4B Gemma 4 26B A4B Q2 15 tok/s 15 tok/s +0% 11.6 GB Xybrid CLI community 2026-01-13
Phi-4 Medium Phi-4 Medium Q6 15 tok/s 14 tok/s +7% 12.4 GB Ollama editorial 2026-02-18
👨‍💻 Laguna XS.2 Q2 15 tok/s 14 tok/s +7% 11.8 GB Ollama community 2026-04-07
🎨 FLUX.1 Schnell Q6 15 tok/s 16 tok/s -6% 9.9 GB LM Studio community 2026-01-01
← All benchmarks