MacBook Air M1 8GB

macOS Mid tier · Apple M1 · 8 GB RAM · 68.25 GB/s bandwidth
View device page →
BENCHMARK RESULTS (85)
Model Quant Measured Estimated RAM used App Source Date
SmolLM2 135M SmolLM2 135M Q8 239 tok/s 200 tok/s +20% 0.2 GB Jan community 2026-02-10
🔢 BGE Small FP16 218 tok/s 200 tok/s +9% 0.1 GB Xybrid CLI community 2026-04-21
🗣️ KittenTTS Nano FP16 215 tok/s 200 tok/s +8% 0.1 GB Piper community 2026-03-02
🔢 all-MiniLM-L6-v2 FP16 203 tok/s 200 tok/s +2% 0.1 GB LM Studio community 2026-03-01
Whisper Tiny Whisper Tiny FP16 200 tok/s 200 tok/s +0% 0.2 GB MacWhisper editorial 2026-03-15
Wav2Vec2 Base Wav2Vec2 Base FP16 198 tok/s 200 tok/s -1% 0.3 GB Xybrid CLI editorial 2026-02-23
🔢 Nomic Embed Text FP16 197 tok/s 200 tok/s -1% 0.3 GB LM Studio community 2026-01-19
SmolLM2 135M SmolLM2 135M FP16 194 tok/s 200 tok/s -3% 0.3 GB Xybrid CLI community 2026-05-08
Whisper Tiny Whisper Tiny FP16 185 tok/s 200 tok/s -7% 0.1 GB MacWhisper community 2026-03-13
🗣️ KittenTTS Mini FP16 179 tok/s 200 tok/s -10% 0.2 GB Xybrid CLI community 2026-05-12
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 177 tok/s 180 tok/s -2% 0.4 GB Xybrid CLI community 2026-04-03
🗣️ Kokoro 82M FP16 174 tok/s 190 tok/s -8% 0.5 GB Xybrid CLI community 2026-02-23
Whisper Small Whisper Small FP16 130 tok/s 139 tok/s -6% 0.6 GB Xybrid CLI community 2026-05-14
🔢 GTE Large FP16 106 tok/s 102 tok/s +4% 0.8 GB Jan community 2026-03-15
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 105 tok/s 57 tok/s +84% 0.9 GB Ollama editorial 2026-03-15
SmolLM2 360M SmolLM2 360M Q8 90 tok/s 74 tok/s +22% 0.6 GB Ollama community 2026-03-01
Ternary Bonsai 4B Ternary Bonsai 4B Q2 84 tok/s 79 tok/s +6% 0.9 GB Xybrid CLI community 2026-02-07
SmolLM2 360M SmolLM2 360M FP16 74 tok/s 74 tok/s +0% 1.2 GB Jan community 2026-05-27
👁️ SmolVLM 500M FP16 66 tok/s 62 tok/s +6% 1.3 GB LM Studio community 2026-01-16
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 63 tok/s 57 tok/s +11% 0.8 GB LM Studio community 2026-04-04
🗣️ OuteTTS 0.3 500M FP16 60 tok/s 68 tok/s -12% 1.1 GB Piper editorial 2026-02-10
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 59 tok/s 57 tok/s +4% 1.5 GB LM Studio editorial 2026-02-23
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 54 tok/s 57 tok/s -5% 1.4 GB Jan community 2026-01-18
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 53 tok/s 59 tok/s -10% 1.4 GB Ollama community 2026-01-17
Ternary Bonsai 8B Ternary Bonsai 8B Q2 47 tok/s 43 tok/s +9% 2.0 GB Xybrid CLI community 2026-01-04
🎙️ Distil-Whisper Large V3 FP16 47 tok/s 46 tok/s +2% 1.9 GB MacWhisper editorial 2026-04-02
Whisper Medium Whisper Medium FP16 43 tok/s 46 tok/s -7% 1.8 GB Xybrid CLI community 2026-05-14
🗣️ NeuTTS Air FP16 42 tok/s 46 tok/s -9% 1.8 GB Xybrid CLI community 2026-05-14
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 37 tok/s 38 tok/s -3% 2.1 GB Xybrid CLI community 2026-05-14
🎨 Stable Diffusion Turbo FP16 37 tok/s 33 tok/s +12% 2.6 GB Xybrid CLI community 2026-05-24
Gemma 3 1B Gemma 3 1B Q8 35 tok/s 31 tok/s +13% 1.4 GB LM Studio community 2026-05-12
Gemma 3 1B Gemma 3 1B FP16 34 tok/s 31 tok/s +10% 2.5 GB Xybrid CLI community 2026-01-14
Bonsai Image 4B Bonsai Image 4B Q2 34 tok/s 38 tok/s -11% 2.0 GB LM Studio community 2026-01-05
TinyLlama 1.1B TinyLlama 1.1B Q8 31 tok/s 31 tok/s +0% 1.5 GB Jan community 2026-01-18
Llama 3.2 1B Llama 3.2 1B Q8 30 tok/s 25 tok/s +20% 1.8 GB Xybrid CLI community 2026-02-08
LFM2.5 1.2B LFM2.5 1.2B FP16 29 tok/s 29 tok/s +0% 2.8 GB Xybrid CLI community 2026-05-16
TinyLlama 1.1B TinyLlama 1.1B FP16 29 tok/s 31 tok/s -6% 2.8 GB LM Studio editorial 2026-05-26
LFM2.5 1.2B LFM2.5 1.2B Q8 29 tok/s 29 tok/s +0% 1.4 GB LM Studio editorial 2026-03-13
SmolLM2 1.7B SmolLM2 1.7B Q8 25 tok/s 20 tok/s +25% 2.2 GB Xybrid CLI editorial 2026-03-16
StableLM 2 1.6B StableLM 2 1.6B Q8 24 tok/s 21 tok/s +14% 1.9 GB Xybrid CLI community 2026-04-02
Llama 3.2 1B Llama 3.2 1B FP16 23 tok/s 25 tok/s -8% 3.1 GB Jan community 2026-05-11
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 23 tok/s 21 tok/s +10% 4.0 GB Ollama community 2026-02-23
Llama 3.2 3B Llama 3.2 3B Q6 23 tok/s 19 tok/s +21% 2.8 GB Xybrid CLI community 2026-01-01
StableLM 2 1.6B StableLM 2 1.6B FP16 22 tok/s 21 tok/s +5% 3.6 GB Jan community 2026-02-10
SmolLM2 1.7B SmolLM2 1.7B FP16 22 tok/s 20 tok/s +10% 4.0 GB Ollama community 2026-02-23
Qwen 2.5 3B Qwen 2.5 3B Q6 22 tok/s 20 tok/s +10% 3.1 GB Jan community 2026-05-24
👨‍💻 StarCoder2 3B Q8 21 tok/s 21 tok/s +0% 3.7 GB LM Studio editorial 2026-04-06
Llama 3.2 3B Llama 3.2 3B Q8 20 tok/s 19 tok/s +5% 3.9 GB Ollama community 2026-03-28
🧠 DeepSeek R1 Distill 1.5B FP16 20 tok/s 21 tok/s -5% 3.9 GB Ollama community 2026-03-15
Qwen 2.5 3B Qwen 2.5 3B Q8 19 tok/s 20 tok/s -5% 4.3 GB Xybrid CLI community 2026-02-23
🗣️ Dia 1.6B FP16 19 tok/s 21 tok/s -10% 3.8 GB Xybrid CLI community 2026-05-13
Whisper Large V3 Whisper Large V3 FP16 19 tok/s 22 tok/s -14% 3.8 GB Xybrid CLI community 2026-04-22
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q8 18 tok/s 20 tok/s -10% 3.9 GB Jan community 2026-04-08
🎨 SDXL Turbo Q8 18 tok/s 18 tok/s +0% 4.0 GB Ollama community 2026-01-02
👁️ Moondream 2B FP16 17 tok/s 18 tok/s -6% 4.5 GB Ollama community 2026-03-15
Gemma 4 E2B Gemma 4 E2B FP16 16 tok/s 15 tok/s +7% 5.1 GB LM Studio editorial 2026-01-14
Qwen 3.5 2B Qwen 3.5 2B FP16 16 tok/s 16 tok/s +0% 4.6 GB Ollama community 2026-01-05
Phi-4 Mini Phi-4 Mini Q8 16 tok/s 16 tok/s +0% 4.9 GB LM Studio community 2026-05-10
Phi-4 Medium Phi-4 Medium Q2 16 tok/s 15 tok/s +7% 6.0 GB Jan community 2026-05-01
Gemma 3n E2B Gemma 3n E2B Q6 16 tok/s 14 tok/s +14% 5.3 GB Jan community 2026-01-02
Gemma 3n E4B Gemma 3n E4B Q4 16 tok/s 14 tok/s +14% 4.8 GB Jan community 2026-05-28
Llama 3.1 8B Llama 3.1 8B Q4 16 tok/s 13 tok/s +23% 5.2 GB Xybrid CLI editorial 2026-01-02
Gemma 3n E2B Gemma 3n E2B Q8 15 tok/s 14 tok/s +7% 5.1 GB LM Studio community 2026-02-24
Gemma 3n E4B Gemma 3n E4B Q5 15 tok/s 14 tok/s +7% 5.3 GB Ollama community 2026-04-08
Qwen 3.5 4B Qwen 3.5 4B Q8 15 tok/s 16 tok/s -6% 5.7 GB Ollama editorial 2026-05-28
Mistral 7B Mistral 7B Q5 15 tok/s 14 tok/s +7% 5.3 GB Ollama community 2026-03-05
Qwen 2.5 7B Qwen 2.5 7B Q4 15 tok/s 13 tok/s +15% 5.4 GB Jan community 2026-04-18
Gemma 3 12B Gemma 3 12B Q3 14 tok/s 13 tok/s +8% 6.8 GB LM Studio editorial 2026-02-24
Mistral Nemo 12B Mistral Nemo 12B Q3 14 tok/s 13 tok/s +8% 5.8 GB Ollama community 2026-04-06
Gemma 4 E4B Gemma 4 E4B Q8 14 tok/s 14 tok/s +0% 5.6 GB LM Studio editorial 2026-04-05
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q5 14 tok/s 13 tok/s +8% 6.3 GB Ollama community 2026-01-18
🎨 Stable Diffusion 3.5 Medium FP16 14 tok/s 15 tok/s -7% 5.2 GB LM Studio editorial 2026-02-11
Gemma 3 4B Gemma 3 4B Q6 14 tok/s 14 tok/s +0% 4.1 GB Jan community 2026-04-09
Gemma 3 4B Gemma 3 4B Q8 13 tok/s 14 tok/s -7% 5.7 GB LM Studio editorial 2026-02-10
Qwen 2.5 7B Qwen 2.5 7B Q5 13 tok/s 13 tok/s +0% 6.3 GB Xybrid CLI community 2026-01-17
🧠 DeepSeek R1 Distill 7B Q5 13 tok/s 13 tok/s +0% 5.4 GB LM Studio community 2026-02-25
🧠 Qwen3 8B Q5 13 tok/s 12 tok/s +8% 6.0 GB Xybrid CLI community 2026-02-09
👁️ LLaVA 1.6 7B Q6 13 tok/s 12 tok/s +8% 6.4 GB Jan community 2026-04-17
Llama 3.1 8B Llama 3.1 8B Q5 12 tok/s 13 tok/s -8% 6.0 GB Jan community 2026-04-10
👨‍💻 DeepSeek Coder 6.7B Q6 12 tok/s 13 tok/s -8% 6.3 GB LM Studio community 2026-04-19
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q5 12 tok/s 13 tok/s -8% 6.0 GB Xybrid CLI community 2026-02-22
🎨 FLUX.1 Schnell Q3 12 tok/s 13 tok/s -8% 6.0 GB Xybrid CLI community 2026-05-16
Qwen 3.5 9B Qwen 3.5 9B Q4 11 tok/s 12 tok/s -8% 6.4 GB Ollama community 2026-03-15
LFM2.5 8B A1B LFM2.5 8B A1B Q5 11 tok/s 12 tok/s -8% 6.8 GB Xybrid CLI community 2026-03-17
🧠 DeepSeek R1 Distill 8B Q5 11 tok/s 13 tok/s -15% 5.8 GB LM Studio community 2026-01-04
← All benchmarks