MacBook Air M2 8GB

macOS Mid tier · Apple M2 · 8 GB RAM · 100 GB/s bandwidth
View device page →
BENCHMARK RESULTS (136)
Model Quant Measured Estimated RAM used App Source Date
🔢 all-MiniLM-L6-v2 Q8 237 tok/s 200 tok/s +19% 0.1 GB Jan community 2026-03-12
🗣️ KittenTTS Mini Q8 236 tok/s 200 tok/s +18% 0.1 GB Piper community 2026-03-02
Whisper Small Whisper Small Q8 236 tok/s 200 tok/s +18% 0.3 GB Xybrid CLI community 2026-03-23
🗣️ Kokoro 82M Q8 235 tok/s 200 tok/s +18% 0.3 GB Xybrid CLI community 2026-05-27
Whisper Tiny Whisper Tiny Q8 231 tok/s 200 tok/s +16% 0.1 GB Xybrid CLI community 2026-05-25
Wav2Vec2 Base Wav2Vec2 Base Q8 221 tok/s 200 tok/s +11% 0.2 GB Xybrid CLI community 2026-01-17
🔢 all-MiniLM-L6-v2 FP16 219 tok/s 200 tok/s +10% 0.1 GB Ollama community 2026-01-13
🗣️ KittenTTS Mini FP16 219 tok/s 200 tok/s +10% 0.2 GB Piper community 2026-01-16
🗣️ Kokoro 82M FP16 208 tok/s 200 tok/s +4% 0.4 GB Xybrid CLI community 2026-03-13
🔢 BGE Small Q8 207 tok/s 200 tok/s +4% 0.1 GB LM Studio editorial 2026-04-21
Whisper Tiny Whisper Tiny FP16 205 tok/s 200 tok/s +3% 0.1 GB MacWhisper community 2026-02-11
🔢 Nomic Embed Text Q8 204 tok/s 200 tok/s +2% 0.2 GB Jan community 2026-01-17
SmolLM2 135M SmolLM2 135M Q8 203 tok/s 200 tok/s +2% 0.2 GB Jan community 2026-03-28
🗣️ KittenTTS Nano Q8 201 tok/s 200 tok/s +1% 0.1 GB Xybrid CLI community 2026-05-12
Whisper Tiny Whisper Tiny FP16 200 tok/s 200 tok/s +0% 0.2 GB MacWhisper editorial 2026-02-28
SmolLM2 135M SmolLM2 135M FP16 200 tok/s 200 tok/s +0% 0.3 GB Ollama community 2026-01-02
🔢 Nomic Embed Text FP16 189 tok/s 200 tok/s -5% 0.3 GB Ollama editorial 2026-04-18
🗣️ KittenTTS Nano FP16 188 tok/s 200 tok/s -6% 0.1 GB Xybrid CLI community 2026-03-26
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 185 tok/s 200 tok/s -7% 0.5 GB Jan community 2026-05-21
🔢 BGE Small FP16 182 tok/s 200 tok/s -9% 0.1 GB Jan community 2026-03-28
🔢 GTE Large Q8 180 tok/s 149 tok/s +21% 0.4 GB Ollama community 2026-03-28
Whisper Small Whisper Small FP16 179 tok/s 200 tok/s -10% 0.6 GB MacWhisper editorial 2026-02-09
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 178 tok/s 200 tok/s -11% 0.5 GB LM Studio editorial 2026-04-20
Wav2Vec2 Base Wav2Vec2 Base FP16 177 tok/s 200 tok/s -11% 0.3 GB MacWhisper editorial 2026-03-14
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 152 tok/s 83 tok/s +83% 0.9 GB Ollama editorial 2026-02-28
🔢 GTE Large FP16 147 tok/s 149 tok/s -1% 0.8 GB Jan community 2026-05-25
SmolLM2 360M SmolLM2 360M Q8 123 tok/s 109 tok/s +13% 0.8 GB Jan community 2026-05-28
SmolLM2 360M SmolLM2 360M FP16 120 tok/s 109 tok/s +10% 1.0 GB Ollama community 2026-03-02
🗣️ OuteTTS 0.3 500M Q8 120 tok/s 100 tok/s +20% 0.7 GB Piper community 2026-02-19
Ternary Bonsai 4B Ternary Bonsai 4B Q2 110 tok/s 116 tok/s -5% 1.1 GB Jan community 2026-02-24
👁️ SmolVLM 500M Q8 109 tok/s 91 tok/s +20% 0.7 GB Xybrid CLI community 2026-01-04
Ternary Bonsai 4B Ternary Bonsai 4B Q2 106 tok/s 116 tok/s -9% 1.1 GB LM Studio editorial 2026-05-23
👁️ SmolVLM 500M FP16 101 tok/s 91 tok/s +11% 1.2 GB Jan community 2026-05-12
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B Q8 100 tok/s 83 tok/s +20% 0.9 GB Xybrid CLI editorial 2026-02-18
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 94 tok/s 83 tok/s +13% 0.9 GB LM Studio editorial 2026-02-25
🗣️ OuteTTS 0.3 500M FP16 92 tok/s 100 tok/s -8% 1.3 GB Piper editorial 2026-04-21
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 92 tok/s 86 tok/s +7% 1.4 GB Jan community 2026-02-28
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 88 tok/s 83 tok/s +6% 1.4 GB Ollama community 2026-05-11
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 81 tok/s 83 tok/s -2% 1.4 GB Jan community 2026-05-24
🎙️ Distil-Whisper Large V3 Q8 80 tok/s 67 tok/s +19% 1.0 GB Xybrid CLI community 2026-03-16
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 79 tok/s 86 tok/s -8% 1.5 GB LM Studio editorial 2026-04-21
Whisper Medium Whisper Medium Q8 75 tok/s 67 tok/s +12% 0.9 GB MacWhisper community 2026-02-11
🗣️ NeuTTS Air FP16 73 tok/s 67 tok/s +9% 1.7 GB Xybrid CLI editorial 2026-02-10
🗣️ NeuTTS Air Q8 71 tok/s 67 tok/s +6% 0.9 GB Xybrid CLI community 2026-05-12
Ternary Bonsai 8B Ternary Bonsai 8B Q2 70 tok/s 63 tok/s +11% 1.8 GB Jan community 2026-05-12
Ternary Bonsai 8B Ternary Bonsai 8B Q2 67 tok/s 63 tok/s +6% 1.7 GB Xybrid CLI community 2026-01-04
Whisper Medium Whisper Medium FP16 64 tok/s 67 tok/s -4% 1.6 GB Xybrid CLI community 2026-04-03
Bonsai Image 4B Bonsai Image 4B Q1 63 tok/s 56 tok/s +13% 1.3 GB LM Studio editorial 2026-05-11
Bonsai Image 4B Bonsai Image 4B Q2 62 tok/s 56 tok/s +11% 2.1 GB Xybrid CLI community 2026-03-14
Qwen 3.5 0.8B Qwen 3.5 0.8B Q8 62 tok/s 56 tok/s +11% 1.0 GB LM Studio community 2026-01-20
🎙️ Distil-Whisper Large V3 FP16 61 tok/s 67 tok/s -9% 1.7 GB MacWhisper editorial 2026-02-11
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 57 tok/s 56 tok/s +2% 2.3 GB Jan community 2026-04-21
Gemma 3 1B Gemma 3 1B Q8 53 tok/s 45 tok/s +18% 1.4 GB LM Studio community 2026-03-04
LFM2.5 1.2B LFM2.5 1.2B Q8 53 tok/s 43 tok/s +23% 1.5 GB Xybrid CLI community 2026-04-20
🎨 Stable Diffusion Turbo Q8 53 tok/s 48 tok/s +10% 1.3 GB Xybrid CLI community 2026-02-19
🎨 Stable Diffusion Turbo FP16 49 tok/s 48 tok/s +2% 2.3 GB LM Studio editorial 2026-05-11
Gemma 3 1B Gemma 3 1B FP16 48 tok/s 45 tok/s +7% 2.3 GB Xybrid CLI community 2026-01-05
TinyLlama 1.1B TinyLlama 1.1B Q8 46 tok/s 45 tok/s +2% 1.4 GB Jan community 2026-05-11
TinyLlama 1.1B TinyLlama 1.1B FP16 43 tok/s 45 tok/s -4% 2.6 GB Ollama community 2026-02-12
LFM2.5 1.2B LFM2.5 1.2B FP16 41 tok/s 43 tok/s -5% 2.8 GB Ollama community 2026-03-15
Llama 3.2 1B Llama 3.2 1B Q8 39 tok/s 37 tok/s +5% 1.7 GB LM Studio community 2026-01-02
Whisper Large V3 Whisper Large V3 Q8 39 tok/s 32 tok/s +22% 2.1 GB MacWhisper editorial 2026-04-07
Llama 3.2 1B Llama 3.2 1B FP16 38 tok/s 37 tok/s +3% 3.4 GB Jan community 2026-05-25
StableLM 2 1.6B StableLM 2 1.6B Q8 36 tok/s 30 tok/s +20% 1.9 GB Ollama community 2026-04-09
Qwen 2.5 3B Qwen 2.5 3B Q6 36 tok/s 29 tok/s +24% 3.1 GB Xybrid CLI community 2026-03-15
👨‍💻 StarCoder2 3B Q6 36 tok/s 30 tok/s +20% 2.8 GB LM Studio community 2026-01-14
🗣️ Dia 1.6B Q8 36 tok/s 30 tok/s +20% 2.0 GB Piper community 2026-04-06
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B Q8 35 tok/s 31 tok/s +13% 1.8 GB Xybrid CLI community 2026-04-03
StableLM 2 1.6B StableLM 2 1.6B FP16 34 tok/s 30 tok/s +13% 3.5 GB LM Studio community 2026-02-10
👨‍💻 StarCoder2 3B Q8 33 tok/s 30 tok/s +10% 3.9 GB Xybrid CLI community 2026-05-23
🗣️ Dia 1.6B FP16 33 tok/s 30 tok/s +10% 3.7 GB Xybrid CLI editorial 2026-02-07
🧠 DeepSeek R1 Distill 1.5B Q8 33 tok/s 30 tok/s +10% 2.0 GB Xybrid CLI community 2026-05-07
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q6 33 tok/s 29 tok/s +14% 3.0 GB LM Studio community 2026-02-26
Qwen 2.5 3B Qwen 2.5 3B Q8 32 tok/s 29 tok/s +10% 4.1 GB Ollama community 2026-02-22
🧠 DeepSeek R1 Distill 1.5B FP16 32 tok/s 30 tok/s +7% 3.8 GB Jan community 2026-02-10
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q8 31 tok/s 29 tok/s +7% 4.2 GB Ollama community 2026-05-12
Llama 3.2 3B Llama 3.2 3B Q6 31 tok/s 28 tok/s +11% 2.9 GB Ollama community 2026-01-03
🎨 SDXL Turbo Q4 31 tok/s 26 tok/s +19% 2.7 GB Xybrid CLI editorial 2026-04-19
SmolLM2 1.7B SmolLM2 1.7B FP16 30 tok/s 29 tok/s +3% 4.0 GB Jan community 2026-03-13
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 30 tok/s 31 tok/s -3% 3.5 GB Jan community 2026-01-11
👁️ Moondream 2B Q8 30 tok/s 27 tok/s +11% 2.5 GB Jan community 2026-05-24
👁️ Moondream 2B FP16 29 tok/s 27 tok/s +7% 3.9 GB Ollama community 2026-02-26
Whisper Large V3 Whisper Large V3 FP16 29 tok/s 32 tok/s -9% 3.9 GB Xybrid CLI community 2026-02-21
SmolLM2 1.7B SmolLM2 1.7B Q8 29 tok/s 29 tok/s +0% 2.0 GB LM Studio editorial 2026-02-08
Llama 3.2 3B Llama 3.2 3B Q8 28 tok/s 28 tok/s +0% 4.0 GB Xybrid CLI community 2026-04-04
Gemma 4 E2B Gemma 4 E2B Q8 26 tok/s 22 tok/s +18% 2.9 GB LM Studio editorial 2026-05-09
Qwen 3.5 2B Qwen 3.5 2B Q8 26 tok/s 24 tok/s +8% 2.5 GB Ollama community 2026-01-02
Gemma 3n E2B Gemma 3n E2B Q6 25 tok/s 21 tok/s +19% 4.4 GB Ollama community 2026-03-02
Gemma 3n E4B Gemma 3n E4B Q4 25 tok/s 20 tok/s +25% 4.9 GB Ollama community 2026-03-02
Qwen 3.5 2B Qwen 3.5 2B FP16 24 tok/s 24 tok/s +0% 4.6 GB Xybrid CLI community 2026-04-03
Phi-4 Mini Phi-4 Mini Q8 24 tok/s 23 tok/s +4% 4.9 GB Jan community 2026-02-06
🎨 SDXL Turbo Q8 24 tok/s 26 tok/s -8% 4.7 GB Jan community 2026-02-20
Qwen 3.5 4B Qwen 3.5 4B Q6 24 tok/s 23 tok/s +4% 3.4 GB LM Studio community 2026-05-24
Phi-4 Mini Phi-4 Mini Q6 24 tok/s 23 tok/s +4% 3.3 GB Xybrid CLI community 2026-04-04
🧠 DeepSeek R1 Distill 7B Q4 24 tok/s 20 tok/s +20% 5.1 GB Xybrid CLI community 2026-04-20
Mistral 7B Mistral 7B Q4 24 tok/s 20 tok/s +20% 5.0 GB Xybrid CLI community 2026-03-15
🧠 DeepSeek R1 Distill 8B Q4 24 tok/s 19 tok/s +26% 5.3 GB LM Studio editorial 2026-02-10
🎨 Stable Diffusion 3.5 Medium Q8 24 tok/s 22 tok/s +9% 3.4 GB Ollama community 2026-04-23
Gemma 4 E2B Gemma 4 E2B FP16 23 tok/s 22 tok/s +5% 5.2 GB Jan community 2026-02-08
🎨 Stable Diffusion 3.5 Medium FP16 23 tok/s 22 tok/s +5% 5.8 GB Xybrid CLI editorial 2026-03-03
Gemma 3n E2B Gemma 3n E2B Q8 22 tok/s 21 tok/s +5% 6.2 GB Jan community 2026-04-22
Mistral 7B Mistral 7B Q5 22 tok/s 20 tok/s +10% 5.9 GB Ollama community 2026-01-16
Mistral Nemo 12B Mistral Nemo 12B Q2 22 tok/s 19 tok/s +16% 4.7 GB Jan community 2026-02-07
🧠 Qwen3 8B Q4 22 tok/s 18 tok/s +22% 5.2 GB Xybrid CLI editorial 2026-01-01
Phi-4 Medium Phi-4 Medium Q2 22 tok/s 21 tok/s +5% 5.5 GB Jan community 2026-05-19
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q4 22 tok/s 19 tok/s +16% 4.8 GB LM Studio community 2026-01-13
Qwen 2.5 7B Qwen 2.5 7B Q5 21 tok/s 20 tok/s +5% 6.4 GB Xybrid CLI community 2026-05-25
Qwen 3.5 4B Qwen 3.5 4B Q8 21 tok/s 23 tok/s -9% 5.6 GB Xybrid CLI community 2026-04-03
Phi-4 Medium Phi-4 Medium Q2 21 tok/s 21 tok/s +0% 6.0 GB Xybrid CLI editorial 2026-02-25
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q5 21 tok/s 20 tok/s +5% 6.4 GB Xybrid CLI community 2026-01-03
Gemma 3 4B Gemma 3 4B Q6 21 tok/s 20 tok/s +5% 3.7 GB Xybrid CLI community 2026-03-25
Qwen 2.5 7B Qwen 2.5 7B Q4 21 tok/s 20 tok/s +5% 4.7 GB LM Studio community 2026-01-02
Llama 3.1 8B Llama 3.1 8B Q4 21 tok/s 19 tok/s +11% 5.2 GB Ollama community 2026-01-05
Gemma 3 12B Gemma 3 12B Q2 21 tok/s 19 tok/s +11% 4.5 GB Ollama community 2026-01-05
Gemma 4 E4B Gemma 4 E4B Q6 21 tok/s 20 tok/s +5% 4.8 GB Ollama community 2026-03-16
👨‍💻 DeepSeek Coder 6.7B Q5 21 tok/s 19 tok/s +11% 5.6 GB Xybrid CLI editorial 2026-01-22
🎨 FLUX.1 Schnell Q2 21 tok/s 20 tok/s +5% 4.3 GB LM Studio community 2026-05-25
Gemma 3n E4B Gemma 3n E4B Q5 20 tok/s 20 tok/s +0% 6.4 GB Jan community 2026-05-27
Llama 3.1 8B Llama 3.1 8B Q5 20 tok/s 19 tok/s +5% 5.9 GB LM Studio editorial 2026-04-06
Gemma 3 12B Gemma 3 12B Q3 20 tok/s 19 tok/s +5% 6.8 GB Xybrid CLI community 2026-05-28
Mistral Nemo 12B Mistral Nemo 12B Q3 20 tok/s 19 tok/s +5% 5.8 GB LM Studio editorial 2026-01-14
🧠 DeepSeek R1 Distill 7B Q5 20 tok/s 20 tok/s +0% 5.9 GB LM Studio editorial 2026-05-11
👁️ LLaVA 1.6 7B Q6 20 tok/s 18 tok/s +11% 6.7 GB Ollama community 2026-05-12
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q5 20 tok/s 19 tok/s +5% 6.4 GB Jan community 2026-02-06
Qwen 3.5 9B Qwen 3.5 9B Q3 20 tok/s 18 tok/s +11% 4.4 GB Xybrid CLI community 2026-04-05
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q4 20 tok/s 20 tok/s +0% 4.7 GB Jan community 2026-04-05
Gemma 4 E4B Gemma 4 E4B Q8 19 tok/s 20 tok/s -5% 6.4 GB LM Studio editorial 2026-01-02
👨‍💻 DeepSeek Coder 6.7B Q6 19 tok/s 19 tok/s +0% 6.0 GB LM Studio editorial 2026-05-08
🎨 FLUX.1 Schnell Q3 19 tok/s 20 tok/s -5% 6.5 GB Xybrid CLI community 2026-04-04
Gemma 3 4B Gemma 3 4B Q8 18 tok/s 20 tok/s -10% 5.6 GB Ollama community 2026-05-11
Qwen 3.5 9B Qwen 3.5 9B Q4 18 tok/s 18 tok/s +0% 6.1 GB Jan community 2026-03-14
LFM2.5 8B A1B LFM2.5 8B A1B Q5 18 tok/s 18 tok/s +0% 6.8 GB Jan community 2026-04-21
🧠 DeepSeek R1 Distill 8B Q5 18 tok/s 19 tok/s -5% 6.1 GB Xybrid CLI community 2026-01-18
LFM2.5 8B A1B LFM2.5 8B A1B Q4 18 tok/s 18 tok/s +0% 6.0 GB LM Studio editorial 2026-05-07
👁️ LLaVA 1.6 7B Q5 18 tok/s 18 tok/s +0% 5.7 GB LM Studio community 2026-04-21
🧠 Qwen3 8B Q5 16 tok/s 18 tok/s -11% 6.2 GB Jan community 2026-04-10
← All benchmarks