Mac Mini M1 8GB

macOS Mid tier · Apple M1 · 8 GB RAM · 68.25 GB/s bandwidth
View device page →
BENCHMARK RESULTS (69)
Model Quant Measured Estimated RAM used App Source Date
SmolLM2 135M SmolLM2 135M FP16 220 tok/s 200 tok/s +10% 0.3 GB Xybrid CLI community 2026-03-17
Whisper Tiny Whisper Tiny FP16 214 tok/s 200 tok/s +7% 0.1 GB Xybrid CLI community 2026-04-19
Wav2Vec2 Base Wav2Vec2 Base FP16 213 tok/s 200 tok/s +7% 0.3 GB MacWhisper community 2026-05-10
🔢 all-MiniLM-L6-v2 FP16 208 tok/s 200 tok/s +4% 0.1 GB LM Studio community 2026-05-10
Whisper Tiny Whisper Tiny FP16 200 tok/s 200 tok/s +0% 0.2 GB MacWhisper editorial 2026-03-20
🔢 BGE Small FP16 186 tok/s 200 tok/s -7% 0.1 GB LM Studio community 2026-02-10
🗣️ KittenTTS Mini FP16 185 tok/s 200 tok/s -7% 0.2 GB Piper community 2026-03-16
🔢 Nomic Embed Text FP16 183 tok/s 200 tok/s -8% 0.3 GB Jan community 2026-03-01
🗣️ KittenTTS Nano FP16 179 tok/s 200 tok/s -10% 0.1 GB Piper community 2026-02-23
🗣️ Kokoro 82M FP16 169 tok/s 190 tok/s -11% 0.4 GB Piper community 2026-04-20
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 165 tok/s 180 tok/s -8% 0.4 GB Jan community 2026-04-09
Whisper Small Whisper Small FP16 138 tok/s 139 tok/s -1% 0.5 GB Xybrid CLI community 2026-03-01
🔢 GTE Large FP16 109 tok/s 102 tok/s +7% 0.9 GB Xybrid CLI community 2026-05-26
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 105 tok/s 57 tok/s +84% 0.9 GB Ollama editorial 2026-03-20
Ternary Bonsai 4B Ternary Bonsai 4B Q2 84 tok/s 79 tok/s +6% 1.1 GB LM Studio editorial 2026-02-25
SmolLM2 360M SmolLM2 360M FP16 70 tok/s 74 tok/s -5% 1.1 GB Xybrid CLI community 2026-01-21
👁️ SmolVLM 500M FP16 69 tok/s 62 tok/s +11% 1.3 GB Xybrid CLI community 2026-04-22
🗣️ OuteTTS 0.3 500M FP16 64 tok/s 68 tok/s -6% 1.2 GB Xybrid CLI community 2026-05-15
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 63 tok/s 59 tok/s +7% 1.3 GB Ollama community 2026-03-02
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 53 tok/s 57 tok/s -7% 1.6 GB Jan community 2026-03-27
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 51 tok/s 57 tok/s -11% 1.4 GB LM Studio editorial 2026-02-11
🗣️ NeuTTS Air FP16 51 tok/s 46 tok/s +11% 1.9 GB Piper community 2026-02-21
🎙️ Distil-Whisper Large V3 FP16 48 tok/s 46 tok/s +4% 1.6 GB Xybrid CLI community 2026-05-24
Whisper Medium Whisper Medium FP16 43 tok/s 46 tok/s -7% 1.9 GB Xybrid CLI community 2026-03-26
Ternary Bonsai 8B Ternary Bonsai 8B Q2 41 tok/s 43 tok/s -5% 1.7 GB LM Studio community 2026-01-03
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 38 tok/s 38 tok/s +0% 2.0 GB LM Studio editorial 2026-04-04
Gemma 3 1B Gemma 3 1B FP16 34 tok/s 31 tok/s +10% 2.7 GB Ollama community 2026-02-20
Bonsai Image 4B Bonsai Image 4B Q2 34 tok/s 38 tok/s -11% 2.3 GB Xybrid CLI editorial 2026-05-25
🎨 Stable Diffusion Turbo FP16 31 tok/s 33 tok/s -6% 2.5 GB Ollama community 2026-04-21
TinyLlama 1.1B TinyLlama 1.1B FP16 30 tok/s 31 tok/s -3% 2.3 GB Xybrid CLI community 2026-05-08
Llama 3.2 1B Llama 3.2 1B FP16 28 tok/s 25 tok/s +12% 3.4 GB Ollama community 2026-01-16
LFM2.5 1.2B LFM2.5 1.2B FP16 27 tok/s 29 tok/s -7% 2.7 GB LM Studio editorial 2026-02-09
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 23 tok/s 21 tok/s +10% 3.5 GB Ollama community 2026-03-03
StableLM 2 1.6B StableLM 2 1.6B FP16 22 tok/s 21 tok/s +5% 4.2 GB Xybrid CLI community 2026-01-06
SmolLM2 1.7B SmolLM2 1.7B FP16 21 tok/s 20 tok/s +5% 3.9 GB Xybrid CLI community 2026-04-19
👨‍💻 StarCoder2 3B Q8 21 tok/s 21 tok/s +0% 4.1 GB LM Studio editorial 2026-02-27
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q8 21 tok/s 20 tok/s +5% 4.1 GB LM Studio community 2026-05-08
🗣️ Dia 1.6B FP16 21 tok/s 21 tok/s +0% 3.8 GB Piper editorial 2026-05-07
Whisper Large V3 Whisper Large V3 FP16 20 tok/s 22 tok/s -9% 3.6 GB MacWhisper community 2026-02-07
Qwen 2.5 3B Qwen 2.5 3B Q8 19 tok/s 20 tok/s -5% 4.1 GB Ollama community 2026-02-12
🧠 DeepSeek R1 Distill 1.5B FP16 19 tok/s 21 tok/s -10% 4.0 GB LM Studio community 2026-05-27
👁️ Moondream 2B FP16 18 tok/s 18 tok/s +0% 4.3 GB Jan community 2026-02-08
Llama 3.2 3B Llama 3.2 3B Q8 17 tok/s 19 tok/s -11% 4.2 GB LM Studio community 2026-02-10
🎨 SDXL Turbo Q8 17 tok/s 18 tok/s -6% 4.1 GB Xybrid CLI community 2026-03-27
Gemma 4 E2B Gemma 4 E2B FP16 16 tok/s 15 tok/s +7% 5.2 GB Jan community 2026-02-07
Qwen 3.5 2B Qwen 3.5 2B FP16 16 tok/s 16 tok/s +0% 5.1 GB Ollama community 2026-04-11
🎨 Stable Diffusion 3.5 Medium FP16 16 tok/s 15 tok/s +7% 5.9 GB LM Studio editorial 2026-03-03
Gemma 3 12B Gemma 3 12B Q3 15 tok/s 13 tok/s +15% 6.0 GB LM Studio editorial 2026-02-10
Phi-4 Mini Phi-4 Mini Q8 15 tok/s 16 tok/s -6% 4.7 GB LM Studio community 2026-05-26
Gemma 3 4B Gemma 3 4B Q8 14 tok/s 14 tok/s +0% 6.1 GB LM Studio editorial 2026-03-01
Gemma 4 E4B Gemma 4 E4B Q8 14 tok/s 14 tok/s +0% 5.3 GB Ollama community 2026-02-08
Qwen 3.5 4B Qwen 3.5 4B Q8 14 tok/s 16 tok/s -12% 5.1 GB LM Studio editorial 2026-02-11
Mistral 7B Mistral 7B Q5 14 tok/s 14 tok/s +0% 5.5 GB LM Studio editorial 2026-04-04
Gemma 3n E4B Gemma 3n E4B Q5 13 tok/s 14 tok/s -7% 5.4 GB Jan community 2026-04-03
Qwen 2.5 7B Qwen 2.5 7B Q5 13 tok/s 13 tok/s +0% 5.7 GB LM Studio editorial 2026-05-11
Llama 3.1 8B Llama 3.1 8B Q5 13 tok/s 13 tok/s +0% 6.7 GB Jan community 2026-04-21
🧠 DeepSeek R1 Distill 7B Q5 13 tok/s 13 tok/s +0% 6.1 GB Jan community 2026-04-18
Phi-4 Medium Phi-4 Medium Q2 13 tok/s 15 tok/s -13% 5.2 GB Jan community 2026-04-07
Gemma 3n E2B Gemma 3n E2B Q8 12 tok/s 14 tok/s -14% 5.8 GB Jan community 2026-02-20
Mistral Nemo 12B Mistral Nemo 12B Q3 12 tok/s 13 tok/s -8% 6.7 GB Jan community 2026-03-24
Qwen 3.5 9B Qwen 3.5 9B Q4 12 tok/s 12 tok/s +0% 6.3 GB Ollama community 2026-02-11
LFM2.5 8B A1B LFM2.5 8B A1B Q5 12 tok/s 12 tok/s +0% 6.0 GB Xybrid CLI community 2026-04-03
🧠 DeepSeek R1 Distill 8B Q5 12 tok/s 13 tok/s -8% 5.6 GB LM Studio community 2026-04-22
👨‍💻 DeepSeek Coder 6.7B Q6 12 tok/s 13 tok/s -8% 6.6 GB Jan community 2026-03-28
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q5 12 tok/s 13 tok/s -8% 6.0 GB Ollama community 2026-03-17
👁️ LLaVA 1.6 7B Q6 12 tok/s 12 tok/s +0% 6.5 GB Jan community 2026-05-26
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q5 12 tok/s 13 tok/s -8% 5.7 GB LM Studio community 2026-05-24
🎨 FLUX.1 Schnell Q3 12 tok/s 13 tok/s -8% 6.3 GB Jan community 2026-03-25
🧠 Qwen3 8B Q5 11 tok/s 12 tok/s -8% 6.9 GB LM Studio editorial 2026-05-27
← All benchmarks