Mac Studio M1 Ultra 64GB

macOS Ultra tier · Apple M1 Ultra · 64 GB RAM · 800 GB/s bandwidth
View device page →
BENCHMARK RESULTS (73)
Model Quant Measured Estimated RAM used App Source Date
Wav2Vec2 Base Wav2Vec2 Base FP16 222 tok/s 200 tok/s +11% 0.3 GB Xybrid CLI community 2026-04-06
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 220 tok/s 200 tok/s +10% 3.9 GB Ollama community 2026-01-14
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 218 tok/s 200 tok/s +9% 1.3 GB Ollama community 2026-03-04
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 217 tok/s 200 tok/s +9% 1.5 GB Xybrid CLI community 2026-03-15
🗣️ NeuTTS Air FP16 217 tok/s 200 tok/s +9% 1.7 GB Piper community 2026-04-09
🎙️ Distil-Whisper Large V3 FP16 217 tok/s 200 tok/s +9% 1.7 GB MacWhisper community 2026-03-28
Llama 3.2 1B Llama 3.2 1B FP16 216 tok/s 200 tok/s +8% 3.3 GB Xybrid CLI community 2026-03-14
Ternary Bonsai 4B Ternary Bonsai 4B Q2 215 tok/s 200 tok/s +8% 0.9 GB Xybrid CLI community 2026-05-27
🗣️ OuteTTS 0.3 500M FP16 215 tok/s 200 tok/s +8% 1.1 GB Xybrid CLI community 2026-01-02
Whisper Tiny Whisper Tiny FP16 214 tok/s 200 tok/s +7% 0.1 GB Xybrid CLI community 2026-05-27
🔢 all-MiniLM-L6-v2 FP16 211 tok/s 200 tok/s +6% 0.1 GB Jan community 2026-03-14
LFM2.5 1.2B LFM2.5 1.2B FP16 209 tok/s 200 tok/s +5% 3.0 GB Ollama editorial 2026-02-26
🗣️ KittenTTS Mini FP16 209 tok/s 200 tok/s +5% 0.2 GB Xybrid CLI community 2026-02-10
StableLM 2 1.6B StableLM 2 1.6B FP16 206 tok/s 200 tok/s +3% 4.3 GB LM Studio community 2026-01-22
SmolLM2 135M SmolLM2 135M FP16 205 tok/s 200 tok/s +3% 0.3 GB Jan community 2026-05-27
Ternary Bonsai 8B Ternary Bonsai 8B Q2 204 tok/s 200 tok/s +2% 2.0 GB Jan community 2026-05-27
Whisper Small Whisper Small FP16 204 tok/s 200 tok/s +2% 0.6 GB MacWhisper community 2026-02-10
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 200 tok/s 200 tok/s +0% 2.2 GB LM Studio community 2026-02-27
TinyLlama 1.1B TinyLlama 1.1B FP16 195 tok/s 200 tok/s -2% 2.7 GB Xybrid CLI community 2026-01-21
Bonsai Image 4B Bonsai Image 4B Q2 195 tok/s 200 tok/s -2% 2.0 GB Xybrid CLI community 2026-04-02
🧠 DeepSeek R1 Distill 1.5B FP16 193 tok/s 200 tok/s -4% 3.9 GB Ollama community 2026-04-20
👁️ SmolVLM 500M FP16 193 tok/s 200 tok/s -4% 1.3 GB Ollama community 2026-04-23
🎨 Stable Diffusion Turbo FP16 192 tok/s 200 tok/s -4% 2.6 GB Xybrid CLI community 2026-01-19
Whisper Medium Whisper Medium FP16 191 tok/s 200 tok/s -4% 1.8 GB Xybrid CLI community 2026-01-19
🔢 BGE Small FP16 190 tok/s 200 tok/s -5% 0.1 GB LM Studio editorial 2026-01-02
🔢 Nomic Embed Text FP16 190 tok/s 200 tok/s -5% 0.3 GB Jan community 2026-05-12
Gemma 3 1B Gemma 3 1B FP16 188 tok/s 200 tok/s -6% 2.8 GB LM Studio editorial 2026-01-04
🗣️ Kokoro 82M FP16 188 tok/s 200 tok/s -6% 0.4 GB Xybrid CLI community 2026-03-01
SmolLM2 1.7B SmolLM2 1.7B FP16 187 tok/s 200 tok/s -6% 3.6 GB Jan community 2026-03-28
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 186 tok/s 200 tok/s -7% 1.5 GB Jan community 2026-04-03
Whisper Large V3 Whisper Large V3 FP16 186 tok/s 200 tok/s -7% 3.7 GB Xybrid CLI community 2026-01-19
Qwen 3.5 2B Qwen 3.5 2B FP16 185 tok/s 190 tok/s -3% 4.4 GB Ollama community 2026-01-02
🗣️ KittenTTS Nano FP16 184 tok/s 200 tok/s -8% 0.1 GB Piper editorial 2026-04-21
👁️ Moondream 2B FP16 182 tok/s 200 tok/s -9% 4.7 GB Jan community 2026-02-19
🗣️ Dia 1.6B FP16 182 tok/s 200 tok/s -9% 4.1 GB Piper community 2026-04-19
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 180 tok/s 200 tok/s -10% 0.5 GB Jan community 2026-03-24
SmolLM2 360M SmolLM2 360M FP16 178 tok/s 200 tok/s -11% 1.1 GB LM Studio editorial 2026-01-06
🔢 GTE Large FP16 178 tok/s 200 tok/s -11% 0.8 GB Xybrid CLI community 2026-05-23
🎨 Stable Diffusion 3.5 Medium FP16 175 tok/s 174 tok/s +1% 5.9 GB Jan community 2026-05-25
Gemma 4 E2B Gemma 4 E2B FP16 172 tok/s 178 tok/s -3% 4.9 GB Xybrid CLI community 2026-05-07
👨‍💻 StarCoder2 3B FP16 141 tok/s 129 tok/s +9% 6.9 GB Xybrid CLI editorial 2026-02-07
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 123 tok/s 125 tok/s -2% 7.7 GB Xybrid CLI community 2026-01-22
Llama 3.2 3B Llama 3.2 3B FP16 122 tok/s 121 tok/s +1% 7.2 GB Ollama community 2026-01-03
🎨 SDXL Turbo FP16 117 tok/s 123 tok/s -5% 7.9 GB Xybrid CLI community 2026-05-13
Qwen 2.5 3B Qwen 2.5 3B FP16 114 tok/s 125 tok/s -9% 8.2 GB Xybrid CLI editorial 2026-05-25
Qwen 3.5 4B Qwen 3.5 4B FP16 97 tok/s 98 tok/s -1% 9.1 GB Ollama community 2026-02-06
Phi-4 Mini Phi-4 Mini FP16 96 tok/s 103 tok/s -7% 9.4 GB Ollama community 2026-03-14
Gemma 3n E2B Gemma 3n E2B FP16 95 tok/s 90 tok/s +6% 9.6 GB Ollama community 2026-04-06
Gemma 4 E4B Gemma 4 E4B FP16 92 tok/s 89 tok/s +3% 10.5 GB LM Studio community 2026-04-06
Gemma 3 4B Gemma 3 4B FP16 81 tok/s 90 tok/s -10% 10.0 GB LM Studio editorial 2026-03-15
Mistral 7B Mistral 7B FP16 60 tok/s 54 tok/s +11% 16.2 GB Ollama community 2026-04-10
🧠 DeepSeek R1 Distill 7B FP16 58 tok/s 52 tok/s +12% 17.0 GB Ollama community 2026-04-09
👨‍💻 DeepSeek Coder 6.7B FP16 58 tok/s 58 tok/s +0% 16.9 GB Xybrid CLI community 2026-01-19
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 57 tok/s 52 tok/s +10% 16.6 GB Ollama community 2026-03-01
Qwen 2.5 7B Qwen 2.5 7B FP16 56 tok/s 52 tok/s +8% 18.6 GB Jan community 2026-02-11
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 55 tok/s 49 tok/s +12% 20.1 GB Ollama community 2026-01-15
Gemma 3n E4B Gemma 3n E4B FP16 54 tok/s 58 tok/s -7% 15.8 GB Jan community 2026-04-10
👁️ LLaVA 1.6 7B FP16 54 tok/s 56 tok/s -4% 17.5 GB Xybrid CLI community 2026-01-22
Llama 3.1 8B Llama 3.1 8B FP16 51 tok/s 50 tok/s +2% 17.8 GB Ollama community 2026-01-04
🧠 DeepSeek R1 Distill 8B FP16 50 tok/s 50 tok/s +0% 19.6 GB Jan community 2026-05-26
LFM2.5 8B A1B LFM2.5 8B A1B FP16 48 tok/s 48 tok/s +0% 20.4 GB LM Studio community 2026-02-27
🧠 Qwen3 8B FP16 43 tok/s 48 tok/s -10% 18.2 GB LM Studio community 2026-02-01
Qwen 3.5 9B Qwen 3.5 9B FP16 40 tok/s 43 tok/s -7% 22.1 GB LM Studio community 2026-03-16
🎨 FLUX.1 Schnell FP16 36 tok/s 34 tok/s +6% 27.5 GB Jan community 2026-03-16
Mistral Nemo 12B Mistral Nemo 12B FP16 35 tok/s 33 tok/s +6% 26.7 GB Ollama community 2026-03-01
Gemma 3 12B Gemma 3 12B FP16 29 tok/s 32 tok/s -9% 28.7 GB Jan community 2026-05-15
Phi-4 Medium Phi-4 Medium FP16 27 tok/s 29 tok/s -7% 29.7 GB Xybrid CLI community 2026-04-04
Gemma 4 26B A4B Gemma 4 26B A4B Q8 26 tok/s 29 tok/s -10% 35.7 GB LM Studio editorial 2026-04-22
👨‍💻 Laguna XS.2 Q8 24 tok/s 23 tok/s +4% 37.3 GB LM Studio community 2026-03-02
Gemma 4 31B Gemma 4 31B Q8 22 tok/s 24 tok/s -8% 38.2 GB Xybrid CLI community 2026-05-13
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q8 21 tok/s 22 tok/s -5% 38.9 GB Jan community 2026-02-22
Llama 4 Scout Llama 4 Scout Q2 20 tok/s 19 tok/s +5% 53.7 GB Ollama editorial 2026-03-05
Qwen3 Coder Next Qwen3 Coder Next Q4 18 tok/s 17 tok/s +6% 52.2 GB Jan community 2026-03-14
← All benchmarks