MacBook Air M1 16GB

macOS High tier · Apple M1 · 16 GB RAM · 68.25 GB/s bandwidth
View device page →
BENCHMARK RESULTS (72)
Model Quant Measured Estimated RAM used App Source Date
🔢 Nomic Embed Text FP16 224 tok/s 200 tok/s +12% 0.3 GB LM Studio community 2026-01-23
🔢 BGE Small FP16 222 tok/s 200 tok/s +11% 0.1 GB LM Studio editorial 2026-01-06
🔢 all-MiniLM-L6-v2 FP16 216 tok/s 200 tok/s +8% 0.1 GB Jan community 2026-01-24
Wav2Vec2 Base Wav2Vec2 Base FP16 203 tok/s 200 tok/s +2% 0.3 GB Xybrid CLI community 2026-04-23
🗣️ KittenTTS Nano FP16 197 tok/s 200 tok/s -1% 0.1 GB Xybrid CLI community 2026-05-09
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 196 tok/s 180 tok/s +9% 0.5 GB LM Studio editorial 2026-04-28
🗣️ Kokoro 82M FP16 188 tok/s 190 tok/s -1% 0.4 GB Xybrid CLI community 2026-01-17
🗣️ KittenTTS Mini FP16 188 tok/s 200 tok/s -6% 0.2 GB Xybrid CLI community 2026-04-04
SmolLM2 135M SmolLM2 135M FP16 180 tok/s 200 tok/s -10% 0.3 GB Jan community 2026-05-12
Whisper Tiny Whisper Tiny FP16 177 tok/s 200 tok/s -11% 0.1 GB MacWhisper community 2026-03-05
Whisper Small Whisper Small FP16 152 tok/s 139 tok/s +9% 0.5 GB MacWhisper editorial 2026-02-10
🔢 GTE Large FP16 93 tok/s 102 tok/s -9% 0.8 GB Ollama editorial 2026-02-11
SmolLM2 360M SmolLM2 360M FP16 80 tok/s 74 tok/s +8% 1.1 GB Jan community 2026-03-17
Ternary Bonsai 4B Ternary Bonsai 4B Q2 73 tok/s 79 tok/s -8% 1.1 GB LM Studio editorial 2026-01-01
🗣️ OuteTTS 0.3 500M FP16 69 tok/s 68 tok/s +1% 1.1 GB Piper community 2026-02-09
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 60 tok/s 57 tok/s +5% 1.5 GB Xybrid CLI community 2026-01-05
👁️ SmolVLM 500M FP16 59 tok/s 62 tok/s -5% 1.2 GB Ollama community 2026-05-28
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 54 tok/s 57 tok/s -5% 1.4 GB Ollama community 2026-03-06
Gemma 3 1B Gemma 3 1B Q8 52 tok/s 31 tok/s +68% 1.5 GB Ollama editorial 2026-03-15
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 52 tok/s 59 tok/s -12% 1.3 GB Ollama community 2026-04-11
🗣️ NeuTTS Air FP16 50 tok/s 46 tok/s +9% 1.6 GB Piper community 2026-01-04
🎙️ Distil-Whisper Large V3 FP16 50 tok/s 46 tok/s +9% 1.6 GB MacWhisper community 2026-02-10
Ternary Bonsai 8B Ternary Bonsai 8B Q2 46 tok/s 43 tok/s +7% 1.7 GB Ollama community 2026-03-01
Whisper Medium Whisper Medium FP16 41 tok/s 46 tok/s -11% 1.9 GB Xybrid CLI community 2026-01-18
Bonsai Image 4B Bonsai Image 4B Q2 40 tok/s 38 tok/s +5% 2.1 GB Jan community 2026-03-14
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 37 tok/s 38 tok/s -3% 2.2 GB Ollama community 2026-04-21
Gemma 3 1B Gemma 3 1B FP16 34 tok/s 31 tok/s +10% 2.5 GB Xybrid CLI editorial 2026-01-02
LFM2.5 1.2B LFM2.5 1.2B FP16 32 tok/s 29 tok/s +10% 2.8 GB Ollama community 2026-02-23
🎨 Stable Diffusion Turbo FP16 31 tok/s 33 tok/s -6% 2.5 GB Ollama community 2026-03-13
Phi-4 Mini Phi-4 Mini Q4 28 tok/s 9 tok/s +211% 2.4 GB LM Studio editorial 2026-03-15
TinyLlama 1.1B TinyLlama 1.1B FP16 28 tok/s 31 tok/s -10% 2.5 GB LM Studio editorial 2026-03-14
Llama 3.2 1B Llama 3.2 1B FP16 24 tok/s 25 tok/s -4% 2.9 GB Xybrid CLI community 2026-05-07
StableLM 2 1.6B StableLM 2 1.6B FP16 22 tok/s 21 tok/s +5% 3.5 GB Jan community 2026-04-23
🗣️ Dia 1.6B FP16 22 tok/s 21 tok/s +5% 3.5 GB Xybrid CLI community 2026-04-23
SmolLM2 1.7B SmolLM2 1.7B FP16 21 tok/s 20 tok/s +5% 3.9 GB Jan community 2026-01-10
👁️ Moondream 2B FP16 20 tok/s 18 tok/s +11% 4.2 GB Jan community 2026-04-18
🧠 DeepSeek R1 Distill 1.5B FP16 19 tok/s 21 tok/s -10% 4.2 GB Xybrid CLI editorial 2026-05-25
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 19 tok/s 21 tok/s -10% 3.7 GB Jan community 2026-05-14
Whisper Large V3 Whisper Large V3 FP16 19 tok/s 22 tok/s -14% 3.4 GB MacWhisper community 2026-03-13
Qwen 3.5 2B Qwen 3.5 2B FP16 18 tok/s 16 tok/s +13% 4.7 GB Xybrid CLI editorial 2026-02-08
Gemma 4 E2B Gemma 4 E2B FP16 17 tok/s 15 tok/s +13% 5.5 GB Xybrid CLI community 2026-05-23
🎨 Stable Diffusion 3.5 Medium FP16 16 tok/s 15 tok/s +7% 5.2 GB Xybrid CLI community 2026-03-14
Qwen 2.5 3B Qwen 2.5 3B FP16 12 tok/s 11 tok/s +9% 7.5 GB Ollama community 2026-05-11
👨‍💻 StarCoder2 3B FP16 12 tok/s 11 tok/s +9% 7.6 GB Xybrid CLI community 2026-03-17
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 11 tok/s 11 tok/s +0% 7.7 GB Ollama community 2026-05-23
🎨 SDXL Turbo FP16 11 tok/s 11 tok/s +0% 8.2 GB Jan community 2026-05-28
Llama 3.2 3B Llama 3.2 3B FP16 10 tok/s 10 tok/s +0% 8.2 GB Jan community 2026-05-25
Gemma 3n E2B Gemma 3n E2B FP16 9 tok/s 8 tok/s +13% 10.7 GB LM Studio community 2026-01-16
Gemma 3 4B Gemma 3 4B FP16 9 tok/s 8 tok/s +13% 10.5 GB Xybrid CLI community 2026-03-13
Qwen 2.5 7B Qwen 2.5 7B Q8 9 tok/s 8 tok/s +13% 8.6 GB Xybrid CLI community 2026-02-08
Qwen 3.5 4B Qwen 3.5 4B FP16 9 tok/s 8 tok/s +13% 8.6 GB Xybrid CLI community 2026-01-01
Phi-4 Mini Phi-4 Mini FP16 9 tok/s 9 tok/s +0% 8.6 GB Ollama community 2026-01-06
👨‍💻 DeepSeek Coder 6.7B Q8 9 tok/s 9 tok/s +0% 8.8 GB Ollama community 2026-04-22
👁️ LLaVA 1.6 7B Q8 9 tok/s 9 tok/s +0% 8.9 GB Ollama community 2026-04-20
Gemma 3n E4B Gemma 3n E4B Q8 8 tok/s 9 tok/s -11% 9.2 GB Jan community 2026-03-25
Llama 3.1 8B Llama 3.1 8B Q8 8 tok/s 8 tok/s +0% 10.5 GB LM Studio community 2026-05-24
Gemma 4 26B A4B Gemma 4 26B A4B Q2 8 tok/s 7 tok/s +14% 12.8 GB Xybrid CLI community 2026-01-03
Qwen 3.5 9B Qwen 3.5 9B Q8 8 tok/s 7 tok/s +14% 11.7 GB Xybrid CLI community 2026-04-19
LFM2.5 8B A1B LFM2.5 8B A1B Q8 8 tok/s 8 tok/s +0% 9.4 GB Xybrid CLI community 2026-04-05
Mistral 7B Mistral 7B Q8 8 tok/s 8 tok/s +0% 9.2 GB LM Studio editorial 2026-05-12
🧠 Qwen3 8B Q8 8 tok/s 8 tok/s +0% 11.2 GB Ollama editorial 2026-01-05
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q8 8 tok/s 8 tok/s +0% 10.4 GB LM Studio editorial 2026-04-05
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q8 8 tok/s 8 tok/s +0% 10.0 GB Jan community 2026-03-13
Mistral Nemo 12B Mistral Nemo 12B Q6 7 tok/s 7 tok/s +0% 12.1 GB Jan community 2026-05-24
Gemma 4 E4B Gemma 4 E4B FP16 7 tok/s 8 tok/s -12% 11.1 GB Xybrid CLI community 2026-04-19
🧠 DeepSeek R1 Distill 7B Q8 7 tok/s 8 tok/s -12% 10.4 GB Jan community 2026-02-21
🧠 DeepSeek R1 Distill 8B Q8 7 tok/s 8 tok/s -12% 10.8 GB LM Studio editorial 2026-04-22
🎨 FLUX.1 Schnell Q6 7 tok/s 7 tok/s +0% 10.9 GB Ollama community 2026-03-15
Gemma 3 12B Gemma 3 12B Q6 6 tok/s 7 tok/s -14% 10.9 GB Ollama editorial 2026-04-18
Gemma 4 31B Gemma 4 31B Q2 6 tok/s 7 tok/s -14% 11.7 GB LM Studio editorial 2026-03-14
👨‍💻 Laguna XS.2 Q2 6 tok/s 6 tok/s +0% 13.8 GB Ollama community 2026-05-18
Phi-4 Medium Phi-4 Medium Q6 5 tok/s 6 tok/s -17% 12.6 GB Jan community 2026-04-07
← All benchmarks