Model Quant Measured Estimated RAM used App Source Date
🔢 all-MiniLM-L6-v2 FP16 219 tok/s 200 tok/s +10% 0.1 GB Xybrid CLI community 2026-04-19
Wav2Vec2 Base Wav2Vec2 Base FP16 212 tok/s 200 tok/s +6% 0.3 GB Xybrid CLI editorial 2026-03-28
🗣️ KittenTTS Mini FP16 209 tok/s 200 tok/s +5% 0.2 GB Xybrid CLI community 2026-02-10
Whisper Tiny Whisper Tiny FP16 209 tok/s 200 tok/s +5% 0.1 GB Whisper Transcription community 2026-05-23
🔢 BGE Small FP16 205 tok/s 200 tok/s +3% 0.1 GB Ollama community 2026-02-11
🗣️ KittenTTS Nano FP16 186 tok/s 200 tok/s -7% 0.1 GB Piper editorial 2026-04-22
SmolLM2 135M SmolLM2 135M FP16 178 tok/s 176 tok/s +1% 0.3 GB Xybrid CLI community 2026-05-26
🔢 Nomic Embed Text FP16 171 tok/s 176 tok/s -3% 0.3 GB Xybrid CLI community 2026-05-15
🗣️ Kokoro 82M FP16 146 tok/s 132 tok/s +11% 0.4 GB Piper community 2026-02-20
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 129 tok/s 125 tok/s +3% 0.4 GB Ollama editorial 2026-05-11
Whisper Small Whisper Small FP16 101 tok/s 97 tok/s +4% 0.6 GB Whisper Transcription community 2026-03-12
🔢 GTE Large FP16 64 tok/s 71 tok/s -10% 0.7 GB Xybrid CLI community 2026-05-24
Ternary Bonsai 4B Ternary Bonsai 4B Q2 61 tok/s 55 tok/s +11% 1.0 GB Xybrid CLI editorial 2026-01-03
SmolLM2 360M SmolLM2 360M FP16 58 tok/s 52 tok/s +12% 1.0 GB Xybrid CLI editorial 2026-01-04
🗣️ OuteTTS 0.3 500M FP16 47 tok/s 48 tok/s -2% 1.2 GB Xybrid CLI community 2026-04-19
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 44 tok/s 40 tok/s +10% 1.5 GB Xybrid CLI community 2026-03-16
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 43 tok/s 40 tok/s +8% 1.3 GB Ollama community 2026-03-01
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 40 tok/s 41 tok/s -2% 1.2 GB Xybrid CLI community 2026-05-09
👁️ SmolVLM 500M FP16 40 tok/s 43 tok/s -7% 1.3 GB Ollama editorial 2026-04-19
🗣️ NeuTTS Air FP16 34 tok/s 32 tok/s +6% 1.6 GB Piper community 2026-04-05
🎙️ Distil-Whisper Large V3 FP16 33 tok/s 32 tok/s +3% 1.9 GB Xybrid CLI editorial 2026-01-21
Ternary Bonsai 8B Ternary Bonsai 8B Q2 32 tok/s 30 tok/s +7% 2.1 GB Xybrid CLI community 2026-01-03
Whisper Medium Whisper Medium FP16 32 tok/s 32 tok/s +0% 1.8 GB Whisper Transcription community 2026-02-23
Bonsai Image 4B Bonsai Image 4B Q2 26 tok/s 26 tok/s +0% 2.0 GB Ollama editorial 2026-04-05
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 25 tok/s 26 tok/s -4% 2.1 GB Xybrid CLI community 2026-02-23
🎨 Stable Diffusion Turbo FP16 23 tok/s 23 tok/s +0% 2.6 GB Xybrid CLI editorial 2026-02-23
Gemma 3 1B Gemma 3 1B FP16 20 tok/s 22 tok/s -9% 2.7 GB Ollama editorial 2026-01-01
TinyLlama 1.1B TinyLlama 1.1B FP16 20 tok/s 22 tok/s -9% 2.6 GB Xybrid CLI community 2026-05-12
LFM2.5 1.2B LFM2.5 1.2B FP16 19 tok/s 20 tok/s -5% 2.8 GB Xybrid CLI community 2026-05-16
Llama 3.2 1B Llama 3.2 1B FP16 18 tok/s 18 tok/s +0% 3.0 GB Ollama community 2026-01-03
Whisper Large V3 Whisper Large V3 FP16 16 tok/s 15 tok/s +7% 3.4 GB Xybrid CLI community 2026-04-08
StableLM 2 1.6B StableLM 2 1.6B FP16 14 tok/s 14 tok/s +0% 4.2 GB Ollama editorial 2026-01-20
SmolLM2 1.7B SmolLM2 1.7B FP16 14 tok/s 14 tok/s +0% 3.9 GB Ollama editorial 2026-05-11
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 14 tok/s 15 tok/s -7% 3.4 GB Xybrid CLI community 2026-02-24
👁️ Moondream 2B FP16 14 tok/s 13 tok/s +8% 4.4 GB Ollama community 2026-05-10
🗣️ Dia 1.6B FP16 13 tok/s 14 tok/s -7% 4.1 GB Piper community 2026-02-20
Qwen 3.5 2B Qwen 3.5 2B FP16 12 tok/s 11 tok/s +9% 5.0 GB Xybrid CLI community 2026-04-18
🧠 DeepSeek R1 Distill 1.5B FP16 12 tok/s 14 tok/s -14% 3.7 GB Ollama editorial 2026-02-11
Gemma 3 4B Gemma 3 4B Q8 10 tok/s 10 tok/s +0% 5.4 GB Xybrid CLI community 2026-03-03
Mistral Nemo 12B Mistral Nemo 12B Q3 10 tok/s 9 tok/s +11% 5.9 GB Xybrid CLI community 2026-04-07
Gemma 4 E2B Gemma 4 E2B FP16 10 tok/s 11 tok/s -9% 4.8 GB Xybrid CLI community 2026-04-03
Gemma 4 E4B Gemma 4 E4B Q8 10 tok/s 10 tok/s +0% 5.4 GB Xybrid CLI community 2026-03-24
Qwen 3.5 4B Qwen 3.5 4B Q8 10 tok/s 11 tok/s -9% 5.5 GB Xybrid CLI editorial 2026-05-23
Phi-4 Mini Phi-4 Mini Q8 10 tok/s 11 tok/s -9% 5.2 GB Ollama community 2026-02-11
🎨 Stable Diffusion 3.5 Medium FP16 10 tok/s 10 tok/s +0% 4.9 GB Xybrid CLI community 2026-05-01
Gemma 3n E2B Gemma 3n E2B Q8 9 tok/s 10 tok/s -10% 5.7 GB Xybrid CLI community 2026-01-18
Gemma 3 12B Gemma 3 12B Q3 9 tok/s 9 tok/s +0% 6.7 GB Ollama editorial 2026-02-26
🧠 DeepSeek R1 Distill 7B Q6 9 tok/s 8 tok/s +13% 6.2 GB Ollama community 2026-03-05
🧠 DeepSeek R1 Distill 8B Q6 9 tok/s 8 tok/s +13% 6.8 GB Ollama community 2026-02-12
🧠 Qwen3 8B Q6 9 tok/s 8 tok/s +13% 7.1 GB Ollama editorial 2026-01-05
Phi-4 Medium Phi-4 Medium Q3 9 tok/s 8 tok/s +13% 7.3 GB Ollama community 2026-02-22
👨‍💻 StarCoder2 3B FP16 9 tok/s 8 tok/s +13% 6.7 GB Xybrid CLI community 2026-01-03
👁️ LLaVA 1.6 7B Q6 9 tok/s 9 tok/s +0% 5.8 GB Ollama community 2026-03-03
Gemma 3n E4B Gemma 3n E4B Q6 8 tok/s 8 tok/s +0% 7.5 GB Xybrid CLI community 2026-05-14
Llama 3.1 8B Llama 3.1 8B Q6 8 tok/s 8 tok/s +0% 6.7 GB Ollama community 2026-01-02
Qwen 3.5 9B Qwen 3.5 9B Q5 8 tok/s 8 tok/s +0% 7.4 GB Ollama community 2026-03-17
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 8 tok/s 7 tok/s +14% 6.9 GB Ollama community 2026-04-08
👨‍💻 DeepSeek Coder 6.7B Q6 8 tok/s 9 tok/s -11% 6.2 GB Xybrid CLI community 2026-04-06
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q6 8 tok/s 8 tok/s +0% 7.1 GB Xybrid CLI community 2026-05-15
🎨 FLUX.1 Schnell Q3 8 tok/s 9 tok/s -11% 6.2 GB Xybrid CLI community 2026-04-22
Qwen 2.5 3B Qwen 2.5 3B FP16 7 tok/s 7 tok/s +0% 7.0 GB Ollama community 2026-01-05
Llama 3.2 3B Llama 3.2 3B FP16 7 tok/s 7 tok/s +0% 7.0 GB Ollama community 2026-05-28
Qwen 2.5 7B Qwen 2.5 7B Q6 7 tok/s 8 tok/s -12% 6.2 GB Ollama community 2026-04-22
LFM2.5 8B A1B LFM2.5 8B A1B Q6 7 tok/s 7 tok/s +0% 7.6 GB Xybrid CLI community 2026-02-23
Mistral 7B Mistral 7B Q6 7 tok/s 8 tok/s -12% 6.5 GB Ollama community 2026-04-11
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q6 7 tok/s 8 tok/s -12% 8.0 GB Xybrid CLI community 2026-02-21
🎨 SDXL Turbo FP16 7 tok/s 7 tok/s +0% 7.1 GB Ollama community 2026-02-27