iPhone 15 6GB

iOS Low tier · Apple A16 · 6 GB RAM · 42 GB/s bandwidth
View device page →
BENCHMARK RESULTS (58)
Model Quant Measured Estimated RAM used App Source Date
🔢 all-MiniLM-L6-v2 FP16 219 tok/s 200 tok/s +10% 0.1 GB LocallyAI editorial 2026-03-07
Whisper Tiny Whisper Tiny FP16 200 tok/s 200 tok/s +0% 0.1 GB Whisper Transcription editorial 2026-01-18
🗣️ KittenTTS Nano FP16 191 tok/s 200 tok/s -4% 0.1 GB LocallyAI community 2026-04-06
🔢 BGE Small FP16 189 tok/s 200 tok/s -5% 0.1 GB LocallyAI community 2026-03-15
🗣️ KittenTTS Mini FP16 179 tok/s 184 tok/s -3% 0.2 GB LocallyAI community 2026-05-07
Wav2Vec2 Base Wav2Vec2 Base FP16 137 tok/s 128 tok/s +7% 0.3 GB Whisper Transcription community 2026-01-20
SmolLM2 135M SmolLM2 135M FP16 109 tok/s 109 tok/s +0% 0.3 GB LocallyAI editorial 2026-02-24
🔢 Nomic Embed Text FP16 96 tok/s 109 tok/s -12% 0.3 GB LocallyAI editorial 2026-01-04
🗣️ Kokoro 82M FP16 75 tok/s 82 tok/s -9% 0.4 GB LocallyAI community 2026-04-08
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 72 tok/s 77 tok/s -6% 0.4 GB LocallyAI community 2026-01-19
Whisper Small Whisper Small FP16 53 tok/s 60 tok/s -12% 0.5 GB Whisper Transcription community 2026-03-13
🔢 GTE Large FP16 40 tok/s 44 tok/s -9% 0.7 GB LocallyAI community 2026-02-09
Ternary Bonsai 4B Ternary Bonsai 4B Q2 33 tok/s 34 tok/s -3% 0.9 GB LocallyAI community 2026-02-08
SmolLM2 360M SmolLM2 360M FP16 32 tok/s 32 tok/s +0% 1.0 GB LocallyAI community 2026-02-07
👁️ SmolVLM 500M FP16 28 tok/s 27 tok/s +4% 1.2 GB LocallyAI community 2026-02-11
🗣️ OuteTTS 0.3 500M FP16 27 tok/s 29 tok/s -7% 1.1 GB LocallyAI community 2026-01-01
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 25 tok/s 25 tok/s +0% 1.5 GB LocallyAI community 2026-04-23
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 24 tok/s 25 tok/s -4% 1.4 GB LocallyAI community 2026-01-17
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 23 tok/s 25 tok/s -8% 1.4 GB LocallyAI community 2026-03-17
Whisper Medium Whisper Medium FP16 22 tok/s 20 tok/s +10% 1.8 GB Whisper Transcription community 2026-05-12
🗣️ NeuTTS Air FP16 19 tok/s 20 tok/s -5% 1.8 GB LocallyAI community 2026-03-17
🎙️ Distil-Whisper Large V3 FP16 19 tok/s 20 tok/s -5% 1.8 GB Whisper Transcription community 2026-04-21
Whisper Large V3 Whisper Large V3 Q8 17 tok/s 18 tok/s -6% 1.9 GB Whisper Transcription community 2026-04-19
SmolLM2 1.7B SmolLM2 1.7B Q8 16 tok/s 16 tok/s +0% 2.0 GB LocallyAI community 2026-05-28
Ternary Bonsai 8B Ternary Bonsai 8B Q2 16 tok/s 18 tok/s -11% 1.9 GB LocallyAI community 2026-04-09
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 16 tok/s 16 tok/s +0% 2.3 GB LocallyAI community 2026-05-24
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B Q8 16 tok/s 17 tok/s -6% 2.0 GB LocallyAI community 2026-01-20
Bonsai Image 4B Bonsai Image 4B Q2 15 tok/s 16 tok/s -6% 2.3 GB LocallyAI editorial 2026-01-28
Gemma 3 1B Gemma 3 1B FP16 14 tok/s 13 tok/s +8% 2.4 GB LocallyAI community 2026-01-01
TinyLlama 1.1B TinyLlama 1.1B FP16 14 tok/s 13 tok/s +8% 2.5 GB LocallyAI editorial 2026-02-10
StableLM 2 1.6B StableLM 2 1.6B Q8 14 tok/s 16 tok/s -12% 2.0 GB LocallyAI editorial 2026-01-05
🧠 DeepSeek R1 Distill 1.5B Q8 14 tok/s 16 tok/s -12% 2.2 GB LocallyAI community 2026-04-22
👁️ Moondream 2B Q8 14 tok/s 15 tok/s -7% 2.5 GB LocallyAI editorial 2026-05-28
🎨 Stable Diffusion Turbo FP16 14 tok/s 14 tok/s +0% 2.7 GB LocallyAI community 2026-04-20
🎨 SDXL Turbo Q4 14 tok/s 13 tok/s +8% 2.7 GB LocallyAI community 2026-01-02
🗣️ Dia 1.6B Q8 14 tok/s 16 tok/s -12% 2.0 GB LocallyAI editorial 2026-01-05
Qwen 2.5 7B Qwen 2.5 7B Q2 13 tok/s 12 tok/s +8% 2.7 GB LocallyAI community 2026-01-05
Qwen 3.5 2B Qwen 3.5 2B Q8 13 tok/s 13 tok/s +0% 2.8 GB LocallyAI community 2026-04-21
Qwen 3.5 4B Qwen 3.5 4B Q4 13 tok/s 12 tok/s +8% 2.8 GB LocallyAI community 2026-01-02
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q6 13 tok/s 12 tok/s +8% 2.8 GB LocallyAI community 2026-02-09
👨‍💻 DeepSeek Coder 6.7B Q2 13 tok/s 13 tok/s +0% 2.7 GB LocallyAI community 2026-05-01
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q2 13 tok/s 12 tok/s +8% 3.2 GB LocallyAI community 2026-01-17
LFM2.5 1.2B LFM2.5 1.2B FP16 12 tok/s 13 tok/s -8% 3.0 GB LocallyAI community 2026-03-01
Gemma 3 4B Gemma 3 4B Q4 12 tok/s 12 tok/s +0% 2.8 GB LocallyAI community 2026-01-03
Llama 3.1 8B Llama 3.1 8B Q2 12 tok/s 11 tok/s +9% 3.0 GB LocallyAI community 2026-01-05
Gemma 4 E2B Gemma 4 E2B Q8 12 tok/s 12 tok/s +0% 2.8 GB LocallyAI community 2026-03-14
Mistral 7B Mistral 7B Q2 12 tok/s 13 tok/s -8% 2.9 GB LocallyAI community 2026-03-25
👨‍💻 StarCoder2 3B Q6 12 tok/s 12 tok/s +0% 2.6 GB LocallyAI community 2026-01-05
👁️ LLaVA 1.6 7B Q2 12 tok/s 13 tok/s -8% 2.7 GB LocallyAI community 2026-03-15
Llama 3.2 1B Llama 3.2 1B FP16 11 tok/s 11 tok/s +0% 3.0 GB LocallyAI editorial 2026-01-16
Qwen 2.5 3B Qwen 2.5 3B Q6 11 tok/s 12 tok/s -8% 3.1 GB LocallyAI community 2026-03-24
Llama 3.2 3B Llama 3.2 3B Q6 11 tok/s 11 tok/s +0% 3.3 GB LocallyAI community 2026-05-24
🧠 DeepSeek R1 Distill 7B Q2 11 tok/s 12 tok/s -8% 3.2 GB LocallyAI community 2026-02-23
🧠 DeepSeek R1 Distill 8B Q2 11 tok/s 11 tok/s +0% 2.9 GB LocallyAI community 2026-01-05
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q2 11 tok/s 11 tok/s +0% 2.8 GB LocallyAI community 2026-01-06
Phi-4 Mini Phi-4 Mini Q5 10 tok/s 11 tok/s -9% 3.3 GB LocallyAI community 2026-05-23
🧠 Qwen3 8B Q2 10 tok/s 11 tok/s -9% 3.5 GB LocallyAI editorial 2026-01-28
🎨 Stable Diffusion 3.5 Medium Q8 10 tok/s 11 tok/s -9% 3.4 GB LocallyAI editorial 2026-03-24
← All benchmarks