Model Quant Measured Estimated RAM used App Source Date
🔢 BGE Small FP16 223 tok/s 200 tok/s +12% 0.1 GB Ollama community 2026-02-21
🔢 all-MiniLM-L6-v2 FP16 212 tok/s 200 tok/s +6% 0.1 GB Ollama community 2026-01-18
🗣️ KittenTTS Mini FP16 206 tok/s 200 tok/s +3% 0.2 GB Xybrid CLI community 2026-04-22
Whisper Tiny Whisper Tiny FP16 187 tok/s 200 tok/s -6% 0.1 GB Xybrid CLI editorial 2026-05-25
🗣️ KittenTTS Nano FP16 185 tok/s 200 tok/s -7% 0.1 GB Xybrid CLI community 2026-02-21
Wav2Vec2 Base Wav2Vec2 Base FP16 184 tok/s 186 tok/s -1% 0.3 GB Whisper Transcription editorial 2026-04-07
SmolLM2 135M SmolLM2 135M FP16 151 tok/s 158 tok/s -4% 0.3 GB Ollama editorial 2026-01-05
🔢 Nomic Embed Text FP16 150 tok/s 158 tok/s -5% 0.3 GB Ollama community 2026-03-15
🗣️ Kokoro 82M FP16 112 tok/s 119 tok/s -6% 0.4 GB Xybrid CLI community 2026-01-20
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 105 tok/s 112 tok/s -6% 0.4 GB Ollama community 2026-01-07
Whisper Small Whisper Small FP16 88 tok/s 87 tok/s +1% 0.6 GB Whisper Transcription community 2026-05-25
🔢 GTE Large FP16 66 tok/s 64 tok/s +3% 0.8 GB Xybrid CLI community 2026-05-27
SmolLM2 360M SmolLM2 360M FP16 48 tok/s 46 tok/s +4% 1.0 GB Xybrid CLI community 2026-02-11
Ternary Bonsai 4B Ternary Bonsai 4B Q2 45 tok/s 50 tok/s -10% 1.1 GB Xybrid CLI community 2026-05-24
🗣️ OuteTTS 0.3 500M FP16 41 tok/s 43 tok/s -5% 1.1 GB Piper community 2026-01-05
👁️ SmolVLM 500M FP16 40 tok/s 39 tok/s +3% 1.2 GB Ollama community 2026-01-04
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 38 tok/s 36 tok/s +6% 1.4 GB Ollama community 2026-05-09
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 36 tok/s 37 tok/s -3% 1.4 GB Xybrid CLI community 2026-03-22
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 34 tok/s 36 tok/s -6% 1.5 GB Ollama community 2026-02-12
Ternary Bonsai 8B Ternary Bonsai 8B Q2 27 tok/s 27 tok/s +0% 1.9 GB Xybrid CLI community 2026-01-18
🎙️ Distil-Whisper Large V3 FP16 27 tok/s 28 tok/s -4% 1.7 GB Whisper Transcription community 2026-04-06
Bonsai Image 4B Bonsai Image 4B Q2 26 tok/s 24 tok/s +8% 2.1 GB Xybrid CLI community 2026-03-13
🗣️ NeuTTS Air FP16 26 tok/s 28 tok/s -7% 1.8 GB Piper community 2026-02-11
Whisper Medium Whisper Medium FP16 25 tok/s 28 tok/s -11% 1.9 GB Whisper Transcription community 2026-03-27
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 24 tok/s 24 tok/s +0% 2.2 GB Xybrid CLI community 2026-05-26
SmolLM2 1.7B SmolLM2 1.7B Q8 22 tok/s 24 tok/s -8% 2.2 GB Xybrid CLI community 2026-05-13
Gemma 3 1B Gemma 3 1B FP16 21 tok/s 19 tok/s +11% 2.5 GB Ollama editorial 2026-01-05
TinyLlama 1.1B TinyLlama 1.1B FP16 21 tok/s 19 tok/s +11% 2.7 GB Xybrid CLI community 2026-02-19
🎨 Stable Diffusion Turbo FP16 20 tok/s 20 tok/s +0% 2.4 GB Xybrid CLI community 2026-04-19
Qwen 2.5 3B Qwen 2.5 3B Q6 19 tok/s 17 tok/s +12% 2.7 GB Xybrid CLI community 2026-02-09
Qwen 3.5 2B Qwen 3.5 2B Q8 19 tok/s 19 tok/s +0% 2.8 GB Xybrid CLI community 2026-05-27
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q6 19 tok/s 17 tok/s +12% 3.0 GB Ollama community 2026-02-21
👁️ Moondream 2B Q8 19 tok/s 21 tok/s -10% 2.5 GB Ollama editorial 2026-05-26
🎨 SDXL Turbo Q4 19 tok/s 19 tok/s +0% 2.3 GB Xybrid CLI community 2026-05-09
🧠 DeepSeek R1 Distill 8B Q2 18 tok/s 16 tok/s +13% 3.0 GB Ollama community 2026-04-09
🧠 Qwen3 8B Q2 18 tok/s 16 tok/s +13% 2.9 GB Ollama community 2026-03-03
Llama 3.2 1B Llama 3.2 1B FP16 17 tok/s 16 tok/s +6% 3.1 GB Ollama editorial 2026-05-21
LFM2.5 1.2B LFM2.5 1.2B FP16 16 tok/s 18 tok/s -11% 2.6 GB Ollama editorial 2026-02-11
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q2 16 tok/s 16 tok/s +0% 3.1 GB Xybrid CLI community 2026-02-24
Llama 3.2 3B Llama 3.2 3B Q6 15 tok/s 16 tok/s -6% 3.2 GB Ollama community 2026-04-21
Llama 3.1 8B Llama 3.1 8B Q2 15 tok/s 16 tok/s -6% 3.1 GB Ollama editorial 2026-03-17
Gemma 4 E2B Gemma 4 E2B Q8 15 tok/s 17 tok/s -12% 2.8 GB Xybrid CLI community 2026-05-12
Whisper Large V3 Whisper Large V3 FP16 15 tok/s 14 tok/s +7% 4.0 GB Whisper Transcription community 2026-01-06
Qwen 2.5 7B Qwen 2.5 7B Q3 14 tok/s 13 tok/s +8% 3.9 GB Ollama community 2026-05-09
Gemma 4 E4B Gemma 4 E4B Q4 14 tok/s 14 tok/s +0% 3.6 GB Ollama community 2026-02-22
Qwen 3.5 9B Qwen 3.5 9B Q2 14 tok/s 14 tok/s +0% 3.8 GB Xybrid CLI community 2026-01-18
LFM2.5 8B A1B LFM2.5 8B A1B Q2 14 tok/s 15 tok/s -7% 3.4 GB Ollama community 2026-03-14
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 14 tok/s 13 tok/s +8% 3.6 GB Ollama community 2026-04-08
👁️ LLaVA 1.6 7B Q3 14 tok/s 14 tok/s +0% 3.2 GB Ollama community 2026-05-09
🎨 Stable Diffusion 3.5 Medium Q8 14 tok/s 16 tok/s -12% 3.1 GB Xybrid CLI community 2026-04-07
Gemma 3n E2B Gemma 3n E2B Q5 13 tok/s 13 tok/s +0% 3.8 GB Ollama community 2026-01-15
Gemma 3 4B Gemma 3 4B Q5 13 tok/s 14 tok/s -7% 3.5 GB Xybrid CLI community 2026-04-09
🧠 DeepSeek R1 Distill 7B Q3 13 tok/s 13 tok/s +0% 4.0 GB Xybrid CLI community 2026-05-27
Mistral 7B Mistral 7B Q3 13 tok/s 14 tok/s -7% 3.7 GB Ollama community 2026-04-18
👨‍💻 StarCoder2 3B Q8 13 tok/s 13 tok/s +0% 3.5 GB Ollama community 2026-05-28
👨‍💻 DeepSeek Coder 6.7B Q3 13 tok/s 15 tok/s -13% 3.3 GB Ollama editorial 2026-01-04
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q3 13 tok/s 13 tok/s +0% 3.9 GB Ollama community 2026-03-14
🗣️ Dia 1.6B FP16 13 tok/s 13 tok/s +0% 3.6 GB Xybrid CLI community 2026-04-07
StableLM 2 1.6B StableLM 2 1.6B FP16 12 tok/s 13 tok/s -8% 4.2 GB Xybrid CLI community 2026-03-25
Qwen 3.5 4B Qwen 3.5 4B Q6 12 tok/s 13 tok/s -8% 3.6 GB Ollama editorial 2026-02-08
🧠 DeepSeek R1 Distill 1.5B FP16 12 tok/s 13 tok/s -8% 4.2 GB Ollama editorial 2026-04-22
Phi-4 Mini Phi-4 Mini Q6 12 tok/s 14 tok/s -14% 3.6 GB Xybrid CLI community 2026-05-14