Model Quant Measured Estimated RAM used App Source Date
Wav2Vec2 Base Wav2Vec2 Base Q8 250 tok/s 200 tok/s +25% 0.2 GB Xybrid CLI community 2026-04-07
Whisper Tiny Whisper Tiny Q8 245 tok/s 200 tok/s +23% 0.1 GB Xybrid CLI community 2026-02-07
🗣️ KittenTTS Nano Q8 239 tok/s 200 tok/s +20% 0.1 GB Piper community 2026-04-07
🗣️ Kokoro 82M Q8 237 tok/s 200 tok/s +19% 0.3 GB Xybrid CLI community 2026-05-25
SmolLM2 135M SmolLM2 135M Q8 232 tok/s 200 tok/s +16% 0.2 GB Jan community 2026-04-22
🔢 Nomic Embed Text Q8 228 tok/s 200 tok/s +14% 0.2 GB LM Studio editorial 2026-01-21
Whisper Small Whisper Small Q8 228 tok/s 200 tok/s +14% 0.3 GB MacWhisper community 2026-02-23
🔢 BGE Small Q8 227 tok/s 200 tok/s +14% 0.1 GB Jan community 2026-02-06
🗣️ KittenTTS Mini Q8 224 tok/s 200 tok/s +12% 0.1 GB Piper community 2026-02-11
🗣️ KittenTTS Nano FP16 220 tok/s 200 tok/s +10% 0.1 GB Xybrid CLI community 2026-02-08
🗣️ Kokoro 82M FP16 220 tok/s 200 tok/s +10% 0.4 GB Piper community 2026-03-05
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 215 tok/s 200 tok/s +8% 0.5 GB Ollama community 2026-02-20
Wav2Vec2 Base Wav2Vec2 Base FP16 214 tok/s 200 tok/s +7% 0.3 GB Xybrid CLI community 2026-05-27
Whisper Tiny Whisper Tiny FP16 212 tok/s 200 tok/s +6% 0.1 GB MacWhisper community 2026-04-06
🔢 all-MiniLM-L6-v2 Q8 211 tok/s 200 tok/s +6% 0.1 GB LM Studio editorial 2026-01-01
Whisper Small Whisper Small FP16 210 tok/s 200 tok/s +5% 0.5 GB Xybrid CLI community 2026-05-24
🗣️ KittenTTS Mini FP16 206 tok/s 200 tok/s +3% 0.2 GB Piper editorial 2026-05-12
SmolLM2 135M SmolLM2 135M FP16 201 tok/s 200 tok/s +1% 0.3 GB LM Studio editorial 2026-01-22
🔢 Nomic Embed Text FP16 201 tok/s 200 tok/s +1% 0.3 GB Jan community 2026-05-27
🗣️ Kokoro 82M FP16 200 tok/s 200 tok/s +0% 0.5 GB Xybrid CLI editorial 2026-03-02
🔢 BGE Small FP16 194 tok/s 200 tok/s -3% 0.1 GB Xybrid CLI community 2026-03-26
🔢 all-MiniLM-L6-v2 FP16 189 tok/s 200 tok/s -5% 0.1 GB Ollama community 2026-03-15
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 186 tok/s 200 tok/s -7% 0.5 GB LM Studio editorial 2026-04-22
🔢 GTE Large Q8 169 tok/s 149 tok/s +13% 0.4 GB Jan community 2026-02-06
🔢 GTE Large FP16 156 tok/s 149 tok/s +5% 0.8 GB LM Studio editorial 2026-05-07
SmolLM2 360M SmolLM2 360M Q8 130 tok/s 109 tok/s +19% 0.7 GB LM Studio editorial 2026-01-16
Ternary Bonsai 4B Ternary Bonsai 4B Q2 125 tok/s 116 tok/s +8% 1.0 GB Jan community 2026-02-11
Ternary Bonsai 4B Ternary Bonsai 4B Q2 123 tok/s 116 tok/s +6% 1.0 GB Ollama editorial 2026-01-18
SmolLM2 360M SmolLM2 360M FP16 113 tok/s 109 tok/s +4% 1.1 GB Jan community 2026-03-15
🗣️ OuteTTS 0.3 500M Q8 108 tok/s 100 tok/s +8% 0.7 GB Xybrid CLI community 2026-03-26
👁️ SmolVLM 500M Q8 95 tok/s 91 tok/s +4% 0.7 GB Xybrid CLI community 2026-03-25
🗣️ OuteTTS 0.3 500M FP16 93 tok/s 100 tok/s -7% 1.1 GB Piper community 2026-05-25
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 91 tok/s 83 tok/s +10% 1.3 GB Xybrid CLI editorial 2026-02-07
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 88 tok/s 86 tok/s +2% 1.3 GB Jan community 2026-02-08
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 86 tok/s 83 tok/s +4% 0.9 GB LM Studio editorial 2026-01-02
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 84 tok/s 86 tok/s -2% 1.3 GB Xybrid CLI community 2026-03-28
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B Q8 84 tok/s 83 tok/s +1% 0.8 GB Jan community 2026-05-15
Whisper Medium Whisper Medium Q8 82 tok/s 67 tok/s +22% 1.0 GB Xybrid CLI community 2026-04-19
👁️ SmolVLM 500M FP16 81 tok/s 91 tok/s -11% 1.3 GB Ollama community 2026-05-11
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 80 tok/s 83 tok/s -4% 1.5 GB Xybrid CLI community 2026-04-03
🗣️ NeuTTS Air Q8 73 tok/s 67 tok/s +9% 0.9 GB Xybrid CLI community 2026-02-24
🎙️ Distil-Whisper Large V3 Q8 72 tok/s 67 tok/s +7% 0.9 GB MacWhisper community 2026-05-28
Ternary Bonsai 8B Ternary Bonsai 8B Q2 68 tok/s 63 tok/s +8% 1.9 GB Ollama community 2026-01-14
Qwen 3.5 0.8B Qwen 3.5 0.8B Q8 68 tok/s 56 tok/s +21% 1.2 GB Xybrid CLI community 2026-04-18
Llama 3.2 1B Llama 3.2 1B Q8 67 tok/s 37 tok/s +81% 1.8 GB Ollama community 2026-03-01
Ternary Bonsai 8B Ternary Bonsai 8B Q2 66 tok/s 63 tok/s +5% 2.0 GB LM Studio editorial 2026-03-01
🎙️ Distil-Whisper Large V3 FP16 66 tok/s 67 tok/s -1% 1.6 GB Xybrid CLI community 2026-03-01
Whisper Medium Whisper Medium FP16 63 tok/s 67 tok/s -6% 1.7 GB MacWhisper editorial 2026-03-14
🗣️ NeuTTS Air FP16 62 tok/s 67 tok/s -7% 1.7 GB Piper editorial 2026-03-16
🎨 Stable Diffusion Turbo Q8 60 tok/s 48 tok/s +25% 1.5 GB Xybrid CLI community 2026-03-15
Bonsai Image 4B Bonsai Image 4B Q1 60 tok/s 56 tok/s +7% 1.4 GB Ollama community 2026-04-19
Gemma 3 1B Gemma 3 1B Q8 53 tok/s 45 tok/s +18% 1.7 GB LM Studio editorial 2026-02-24
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 52 tok/s 56 tok/s -7% 2.1 GB Ollama editorial 2026-03-13
🎨 Stable Diffusion Turbo FP16 52 tok/s 48 tok/s +8% 2.5 GB Ollama community 2026-02-22
Bonsai Image 4B Bonsai Image 4B Q2 52 tok/s 56 tok/s -7% 2.1 GB Xybrid CLI community 2026-01-19
Phi-4 Mini Phi-4 Mini Q4 48 tok/s 13 tok/s +269% 2.4 GB LM Studio editorial 2026-02-25
TinyLlama 1.1B TinyLlama 1.1B Q8 48 tok/s 45 tok/s +7% 1.5 GB Xybrid CLI community 2026-05-12
LFM2.5 1.2B LFM2.5 1.2B FP16 47 tok/s 43 tok/s +9% 2.8 GB Ollama community 2026-05-12
Llama 3.2 1B Llama 3.2 1B Q8 46 tok/s 37 tok/s +24% 1.7 GB Ollama community 2026-03-05
Gemma 3 1B Gemma 3 1B FP16 43 tok/s 45 tok/s -4% 2.7 GB Ollama community 2026-04-22
LFM2.5 1.2B LFM2.5 1.2B Q8 43 tok/s 43 tok/s +0% 1.5 GB LM Studio community 2026-04-21
TinyLlama 1.1B TinyLlama 1.1B FP16 42 tok/s 45 tok/s -7% 2.5 GB Ollama editorial 2026-04-19
Llama 3.2 1B Llama 3.2 1B FP16 39 tok/s 37 tok/s +5% 2.9 GB Jan community 2026-05-25
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B Q8 38 tok/s 31 tok/s +23% 2.0 GB Ollama community 2026-02-22
Whisper Large V3 Whisper Large V3 Q8 37 tok/s 32 tok/s +16% 1.8 GB Xybrid CLI community 2026-02-09
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 34 tok/s 31 tok/s +10% 4.0 GB Xybrid CLI community 2026-03-15
🧠 DeepSeek R1 Distill 1.5B Q8 33 tok/s 30 tok/s +10% 2.2 GB Ollama community 2026-04-21
🗣️ Dia 1.6B Q8 33 tok/s 30 tok/s +10% 2.0 GB Piper community 2026-02-06
🗣️ Dia 1.6B FP16 32 tok/s 30 tok/s +7% 4.3 GB Xybrid CLI community 2026-05-01
Whisper Large V3 Whisper Large V3 FP16 32 tok/s 32 tok/s +0% 3.4 GB Xybrid CLI editorial 2026-03-01
🧠 DeepSeek R1 Distill 1.5B FP16 31 tok/s 30 tok/s +3% 4.1 GB LM Studio editorial 2026-03-02
StableLM 2 1.6B StableLM 2 1.6B Q8 31 tok/s 30 tok/s +3% 2.3 GB LM Studio editorial 2026-04-20
SmolLM2 1.7B SmolLM2 1.7B Q8 31 tok/s 29 tok/s +7% 2.1 GB Ollama community 2026-04-18
👁️ Moondream 2B FP16 30 tok/s 27 tok/s +11% 4.2 GB Ollama community 2026-03-05
StableLM 2 1.6B StableLM 2 1.6B FP16 27 tok/s 30 tok/s -10% 4.1 GB Jan community 2026-03-27
SmolLM2 1.7B SmolLM2 1.7B FP16 27 tok/s 29 tok/s -7% 4.0 GB Jan community 2026-01-18
Qwen 3.5 2B Qwen 3.5 2B Q8 27 tok/s 24 tok/s +13% 2.8 GB Xybrid CLI community 2026-02-23
👁️ Moondream 2B Q8 27 tok/s 27 tok/s +0% 2.2 GB LM Studio editorial 2026-01-06
Gemma 4 E2B Gemma 4 E2B Q8 26 tok/s 22 tok/s +18% 2.7 GB Xybrid CLI community 2026-01-06
Qwen 3.5 2B Qwen 3.5 2B FP16 25 tok/s 24 tok/s +4% 4.7 GB LM Studio editorial 2026-05-09
🎨 Stable Diffusion 3.5 Medium Q8 23 tok/s 22 tok/s +5% 3.3 GB Ollama community 2026-03-16
🎨 Stable Diffusion 3.5 Medium FP16 21 tok/s 22 tok/s -5% 5.9 GB LM Studio editorial 2026-01-02
Gemma 4 E2B Gemma 4 E2B FP16 20 tok/s 22 tok/s -9% 5.1 GB Jan community 2026-04-08
👨‍💻 StarCoder2 3B Q8 20 tok/s 16 tok/s +25% 3.8 GB LM Studio editorial 2026-02-07
👨‍💻 StarCoder2 3B FP16 18 tok/s 16 tok/s +13% 7.4 GB Xybrid CLI community 2026-04-21
Qwen 2.5 3B Qwen 2.5 3B Q8 18 tok/s 16 tok/s +13% 4.0 GB Jan community 2026-02-07
Llama 3.2 3B Llama 3.2 3B Q8 18 tok/s 15 tok/s +20% 3.8 GB Ollama community 2026-03-05
🎨 SDXL Turbo Q8 18 tok/s 15 tok/s +20% 4.7 GB Jan community 2026-03-15
Qwen 2.5 3B Qwen 2.5 3B FP16 17 tok/s 16 tok/s +6% 7.3 GB LM Studio editorial 2026-05-08
Llama 3.2 3B Llama 3.2 3B FP16 17 tok/s 15 tok/s +13% 7.9 GB Jan community 2026-01-18
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q8 17 tok/s 16 tok/s +6% 4.2 GB Xybrid CLI community 2026-05-14
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 16 tok/s 16 tok/s +0% 7.7 GB Ollama community 2026-03-15
Gemma 3n E4B Gemma 3n E4B Q6 16 tok/s 14 tok/s +14% 7.7 GB Ollama community 2026-03-04
Phi-4 Mini Phi-4 Mini Q8 16 tok/s 13 tok/s +23% 5.7 GB Xybrid CLI community 2026-05-26
👨‍💻 DeepSeek Coder 6.7B Q6 16 tok/s 14 tok/s +14% 6.6 GB LM Studio editorial 2026-02-27
Gemma 3n E4B Gemma 3n E4B Q8 14 tok/s 14 tok/s +0% 9.0 GB Jan community 2026-05-24
👨‍💻 DeepSeek Coder 6.7B Q8 14 tok/s 14 tok/s +0% 9.1 GB Jan community 2026-05-28
🎨 SDXL Turbo FP16 14 tok/s 15 tok/s -7% 7.6 GB LM Studio community 2026-02-11
Gemma 3n E2B Gemma 3n E2B Q8 14 tok/s 11 tok/s +27% 5.7 GB Xybrid CLI community 2026-04-19
Gemma 3 4B Gemma 3 4B Q8 14 tok/s 11 tok/s +27% 5.9 GB Ollama community 2026-02-21
Gemma 3 12B Gemma 3 12B Q5 14 tok/s 11 tok/s +27% 9.8 GB Xybrid CLI community 2026-05-24
Qwen 3.5 4B Qwen 3.5 4B Q8 14 tok/s 12 tok/s +17% 5.1 GB Xybrid CLI community 2026-04-19
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q6 14 tok/s 12 tok/s +17% 6.8 GB Jan community 2026-03-13
🎨 FLUX.1 Schnell Q5 14 tok/s 11 tok/s +27% 9.1 GB Jan community 2026-05-12
Phi-4 Mini Phi-4 Mini FP16 13 tok/s 13 tok/s +0% 8.2 GB LM Studio community 2026-02-25
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q8 13 tok/s 12 tok/s +8% 9.2 GB LM Studio editorial 2026-01-14
Qwen 2.5 7B Qwen 2.5 7B Q6 13 tok/s 12 tok/s +8% 7.1 GB Xybrid CLI community 2026-02-24
LFM2.5 8B A1B LFM2.5 8B A1B Q6 13 tok/s 11 tok/s +18% 6.9 GB Ollama community 2026-04-06
🧠 Qwen3 8B Q6 13 tok/s 11 tok/s +18% 7.6 GB Ollama community 2026-01-14
👁️ LLaVA 1.6 7B Q6 13 tok/s 13 tok/s +0% 7.0 GB Xybrid CLI editorial 2026-04-19
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q6 13 tok/s 12 tok/s +8% 7.7 GB Ollama community 2026-03-15
Gemma 3n E2B Gemma 3n E2B FP16 12 tok/s 11 tok/s +9% 10.1 GB LM Studio editorial 2026-01-05
Gemma 3 4B Gemma 3 4B FP16 12 tok/s 11 tok/s +9% 10.7 GB Xybrid CLI community 2026-04-20
Gemma 3 12B Gemma 3 12B Q6 12 tok/s 11 tok/s +9% 11.3 GB LM Studio community 2026-01-16
Qwen 3.5 4B Qwen 3.5 4B FP16 12 tok/s 12 tok/s +0% 9.4 GB LM Studio editorial 2026-05-10
LFM2.5 8B A1B LFM2.5 8B A1B Q8 12 tok/s 11 tok/s +9% 9.4 GB Xybrid CLI community 2026-02-07
👁️ LLaVA 1.6 7B Q8 12 tok/s 13 tok/s -8% 9.1 GB Jan community 2026-03-26
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q8 12 tok/s 12 tok/s +0% 10.6 GB LM Studio community 2026-02-23
Llama 3.1 8B Llama 3.1 8B Q6 12 tok/s 12 tok/s +0% 7.2 GB Jan community 2026-05-13
Gemma 4 E4B Gemma 4 E4B Q8 12 tok/s 11 tok/s +9% 6.2 GB Jan community 2026-05-25
🧠 DeepSeek R1 Distill 7B Q6 12 tok/s 12 tok/s +0% 6.6 GB Jan community 2026-05-12
Mistral 7B Mistral 7B Q6 12 tok/s 12 tok/s +0% 7.3 GB LM Studio community 2026-05-26
🧠 DeepSeek R1 Distill 8B Q6 12 tok/s 12 tok/s +0% 6.9 GB LM Studio editorial 2026-03-15
Qwen 2.5 7B Qwen 2.5 7B Q8 11 tok/s 12 tok/s -8% 9.6 GB LM Studio community 2026-03-15
Llama 3.1 8B Llama 3.1 8B Q8 11 tok/s 12 tok/s -8% 9.1 GB Xybrid CLI community 2026-03-27
Gemma 4 E4B Gemma 4 E4B FP16 11 tok/s 11 tok/s +0% 11.1 GB Xybrid CLI community 2026-02-24
🧠 DeepSeek R1 Distill 7B Q8 11 tok/s 12 tok/s -8% 10.3 GB Xybrid CLI community 2026-03-26
Mistral 7B Mistral 7B Q8 11 tok/s 12 tok/s -8% 9.7 GB Ollama community 2026-02-12
🧠 DeepSeek R1 Distill 8B Q8 11 tok/s 12 tok/s -8% 10.0 GB Jan community 2026-04-08
🧠 Qwen3 8B Q8 11 tok/s 11 tok/s +0% 9.3 GB LM Studio community 2026-03-01
Mistral Nemo 12B Mistral Nemo 12B Q5 11 tok/s 11 tok/s +0% 9.3 GB Jan community 2026-04-08
Qwen 3.5 9B Qwen 3.5 9B Q6 11 tok/s 10 tok/s +10% 7.9 GB LM Studio editorial 2026-04-06
Mistral Nemo 12B Mistral Nemo 12B Q6 10 tok/s 11 tok/s -9% 10.7 GB LM Studio editorial 2026-02-08
Qwen 3.5 9B Qwen 3.5 9B Q8 10 tok/s 10 tok/s +0% 12.0 GB Xybrid CLI community 2026-01-20
🎨 FLUX.1 Schnell Q6 10 tok/s 11 tok/s -9% 10.5 GB LM Studio editorial 2026-03-13
Phi-4 Medium Phi-4 Medium Q5 10 tok/s 9 tok/s +11% 10.4 GB Xybrid CLI editorial 2026-04-02
Gemma 4 26B A4B Gemma 4 26B A4B Q2 9 tok/s 10 tok/s -10% 11.6 GB LM Studio editorial 2026-02-12
Gemma 4 31B Gemma 4 31B Q2 9 tok/s 10 tok/s -10% 13.2 GB Ollama community 2026-01-17
Phi-4 Medium Phi-4 Medium Q6 9 tok/s 9 tok/s +0% 12.2 GB Jan community 2026-02-10
👨‍💻 Laguna XS.2 Q2 9 tok/s 9 tok/s +0% 11.9 GB Xybrid CLI community 2026-03-28
Gemma 4 26B A4B Gemma 4 26B A4B Q2 9 tok/s 10 tok/s -10% 11.6 GB Xybrid CLI community 2026-01-20
Gemma 4 31B Gemma 4 31B Q2 9 tok/s 10 tok/s -10% 13.3 GB LM Studio editorial 2026-05-25
👨‍💻 Laguna XS.2 Q2 8 tok/s 9 tok/s -11% 12.9 GB Jan community 2026-05-14