iPhone 16 Pro 8GB

iOS Mid tier · Apple A18 Pro · 8 GB RAM · 68 GB/s bandwidth
View device page →
BENCHMARK RESULTS (65)
Model Quant Measured Estimated RAM used App Source Date
Whisper Tiny Whisper Tiny FP16 221 tok/s 200 tok/s +11% 0.1 GB Whisper Transcription community 2026-04-20
Wav2Vec2 Base Wav2Vec2 Base FP16 208 tok/s 200 tok/s +4% 0.2 GB Whisper Transcription community 2026-01-04
Whisper Tiny Whisper Tiny FP16 200 tok/s 200 tok/s +0% 0.1 GB Whisper Transcription editorial 2026-03-05
🔢 all-MiniLM-L6-v2 FP16 200 tok/s 200 tok/s +0% 0.1 GB LocallyAI community 2026-04-02
🔢 BGE Small FP16 199 tok/s 200 tok/s +0% 0.1 GB LocallyAI community 2026-05-10
🗣️ KittenTTS Mini FP16 199 tok/s 200 tok/s +0% 0.2 GB LocallyAI editorial 2026-04-05
🔢 Nomic Embed Text FP16 184 tok/s 176 tok/s +5% 0.3 GB LocallyAI community 2026-01-01
🗣️ KittenTTS Nano FP16 181 tok/s 200 tok/s -9% 0.1 GB LocallyAI community 2026-02-22
SmolLM2 135M SmolLM2 135M FP16 171 tok/s 176 tok/s -3% 0.3 GB LocallyAI community 2026-05-27
🗣️ Kokoro 82M FP16 138 tok/s 132 tok/s +5% 0.4 GB LocallyAI community 2026-03-13
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 135 tok/s 125 tok/s +8% 0.5 GB LocallyAI community 2026-03-14
Whisper Small Whisper Small FP16 99 tok/s 97 tok/s +2% 0.6 GB Whisper Transcription community 2026-05-23
Qwen 2.5 0.5B Qwen 2.5 0.5B Q4 98 tok/s 40 tok/s +145% 0.6 GB LM Studio community 2026-03-05
🔢 GTE Large FP16 70 tok/s 71 tok/s -1% 0.8 GB LocallyAI community 2026-05-25
Gemma 3 1B Gemma 3 1B Q4 62 tok/s 22 tok/s +182% 0.9 GB LM Studio community 2026-03-06
SmolLM2 360M SmolLM2 360M FP16 58 tok/s 52 tok/s +12% 1.0 GB LocallyAI community 2026-03-03
Ternary Bonsai 4B Ternary Bonsai 4B Q2 55 tok/s 55 tok/s +0% 1.0 GB LocallyAI community 2026-01-05
🗣️ OuteTTS 0.3 500M FP16 45 tok/s 48 tok/s -6% 1.3 GB LocallyAI editorial 2026-04-22
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 42 tok/s 40 tok/s +5% 1.5 GB LocallyAI community 2026-01-05
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 39 tok/s 40 tok/s -2% 1.3 GB LocallyAI community 2026-03-01
👁️ SmolVLM 500M FP16 39 tok/s 43 tok/s -9% 1.2 GB LocallyAI community 2026-05-16
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 36 tok/s 41 tok/s -12% 1.4 GB LocallyAI community 2026-03-16
Whisper Medium Whisper Medium FP16 35 tok/s 32 tok/s +9% 1.8 GB Whisper Transcription community 2026-02-19
Ternary Bonsai 8B Ternary Bonsai 8B Q2 32 tok/s 30 tok/s +7% 2.1 GB LocallyAI editorial 2026-04-07
Bonsai Image 4B Bonsai Image 4B Q2 29 tok/s 26 tok/s +12% 2.2 GB LocallyAI community 2026-03-16
🎙️ Distil-Whisper Large V3 FP16 29 tok/s 32 tok/s -9% 1.7 GB Whisper Transcription editorial 2026-02-11
🗣️ NeuTTS Air FP16 28 tok/s 32 tok/s -12% 1.7 GB LocallyAI editorial 2026-03-14
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 26 tok/s 26 tok/s +0% 2.3 GB LocallyAI community 2026-03-16
Gemma 3 1B Gemma 3 1B FP16 24 tok/s 22 tok/s +9% 2.4 GB LocallyAI community 2026-01-06
🎨 Stable Diffusion Turbo FP16 23 tok/s 23 tok/s +0% 2.3 GB LocallyAI community 2026-05-10
LFM2.5 1.2B LFM2.5 1.2B FP16 22 tok/s 20 tok/s +10% 2.6 GB LocallyAI community 2026-02-07
TinyLlama 1.1B TinyLlama 1.1B FP16 22 tok/s 22 tok/s +0% 2.7 GB LocallyAI community 2026-03-17
Qwen 3.5 2B Qwen 3.5 2B Q8 22 tok/s 21 tok/s +5% 2.6 GB LocallyAI editorial 2026-05-10
👁️ Moondream 2B Q8 21 tok/s 24 tok/s -12% 2.4 GB LocallyAI community 2026-03-05
🎨 SDXL Turbo Q4 20 tok/s 22 tok/s -9% 2.8 GB LocallyAI community 2026-02-22
Gemma 4 E2B Gemma 4 E2B Q8 19 tok/s 19 tok/s +0% 2.8 GB LocallyAI community 2026-01-04
🎨 Stable Diffusion 3.5 Medium Q8 18 tok/s 18 tok/s +0% 3.3 GB LocallyAI community 2026-03-28
Llama 3.2 1B Llama 3.2 1B FP16 17 tok/s 18 tok/s -6% 3.1 GB LocallyAI community 2026-03-14
Qwen 3.5 4B Qwen 3.5 4B Q6 16 tok/s 15 tok/s +7% 3.7 GB LocallyAI editorial 2026-01-18
Phi-4 Mini Phi-4 Mini Q6 16 tok/s 15 tok/s +7% 3.5 GB LocallyAI community 2026-02-07
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 16 tok/s 15 tok/s +7% 3.8 GB LocallyAI community 2026-03-13
👁️ LLaVA 1.6 7B Q3 16 tok/s 16 tok/s +0% 3.3 GB LocallyAI editorial 2026-03-28
SmolLM2 1.7B SmolLM2 1.7B FP16 15 tok/s 14 tok/s +7% 4.1 GB LocallyAI community 2026-04-17
Gemma 3 4B Gemma 3 4B Q6 15 tok/s 14 tok/s +7% 3.9 GB LocallyAI community 2026-04-06
Qwen 2.5 7B Qwen 2.5 7B Q3 15 tok/s 14 tok/s +7% 3.5 GB LocallyAI community 2026-01-04
Llama 3.1 8B Llama 3.1 8B Q3 15 tok/s 14 tok/s +7% 3.9 GB LocallyAI community 2026-05-11
👨‍💻 StarCoder2 3B Q8 15 tok/s 14 tok/s +7% 3.9 GB LocallyAI community 2026-04-20
👨‍💻 DeepSeek Coder 6.7B Q3 15 tok/s 16 tok/s -6% 3.8 GB LocallyAI community 2026-03-24
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q3 15 tok/s 14 tok/s +7% 4.2 GB LocallyAI community 2026-01-06
StableLM 2 1.6B StableLM 2 1.6B FP16 14 tok/s 14 tok/s +0% 4.1 GB LocallyAI community 2026-04-22
Gemma 3n E2B Gemma 3n E2B Q5 14 tok/s 14 tok/s +0% 4.2 GB LocallyAI community 2026-04-20
Llama 3.2 3B Llama 3.2 3B Q8 14 tok/s 13 tok/s +8% 4.2 GB LocallyAI community 2026-05-12
Gemma 4 E4B Gemma 4 E4B Q5 14 tok/s 14 tok/s +0% 3.6 GB LocallyAI community 2026-01-04
Qwen 3.5 9B Qwen 3.5 9B Q2 14 tok/s 15 tok/s -7% 3.8 GB LocallyAI community 2026-01-28
LFM2.5 8B A1B LFM2.5 8B A1B Q3 14 tok/s 13 tok/s +8% 4.6 GB LocallyAI community 2026-05-28
Mistral 7B Mistral 7B Q3 14 tok/s 15 tok/s -7% 4.0 GB LocallyAI community 2026-02-24
🧠 DeepSeek R1 Distill 8B Q3 14 tok/s 14 tok/s +0% 4.2 GB LocallyAI community 2026-03-01
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q8 14 tok/s 14 tok/s +0% 4.0 GB LocallyAI editorial 2026-05-08
🗣️ Dia 1.6B FP16 14 tok/s 14 tok/s +0% 4.2 GB LocallyAI community 2026-04-23
Whisper Large V3 Whisper Large V3 FP16 14 tok/s 15 tok/s -7% 3.3 GB Whisper Transcription community 2026-03-26
Qwen 2.5 3B Qwen 2.5 3B Q8 13 tok/s 14 tok/s -7% 4.4 GB LocallyAI community 2026-04-01
🧠 DeepSeek R1 Distill 1.5B FP16 13 tok/s 14 tok/s -7% 3.5 GB LocallyAI community 2026-04-18
🧠 DeepSeek R1 Distill 7B Q3 13 tok/s 14 tok/s -7% 4.2 GB LocallyAI community 2026-03-24
🧠 Qwen3 8B Q3 13 tok/s 14 tok/s -7% 4.0 GB LocallyAI community 2026-05-11
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q3 13 tok/s 14 tok/s -7% 4.2 GB LocallyAI community 2026-04-19
← All benchmarks