Model Quant Measured Estimated RAM used App Source Date
Whisper Tiny Whisper Tiny FP16 218 tok/s 200 tok/s +9% 0.1 GB Xybrid CLI community 2026-01-04
SmolLM2 135M SmolLM2 135M FP16 216 tok/s 200 tok/s +8% 0.3 GB Ollama community 2026-02-20
Wav2Vec2 Base Wav2Vec2 Base FP16 205 tok/s 200 tok/s +3% 0.3 GB Xybrid CLI editorial 2026-02-27
🔢 all-MiniLM-L6-v2 FP16 204 tok/s 200 tok/s +2% 0.1 GB Ollama editorial 2026-03-01
🗣️ KittenTTS Mini FP16 204 tok/s 200 tok/s +2% 0.2 GB Piper editorial 2026-02-26
🔢 Nomic Embed Text FP16 189 tok/s 200 tok/s -5% 0.3 GB Xybrid CLI community 2026-05-15
🔢 BGE Small FP16 188 tok/s 200 tok/s -6% 0.1 GB Ollama community 2026-01-04
🗣️ KittenTTS Nano FP16 183 tok/s 200 tok/s -8% 0.1 GB Xybrid CLI community 2026-05-11
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 138 tok/s 142 tok/s -3% 0.4 GB Xybrid CLI community 2026-03-01
🗣️ Kokoro 82M FP16 136 tok/s 150 tok/s -9% 0.4 GB Xybrid CLI community 2026-02-22
Whisper Small Whisper Small FP16 98 tok/s 110 tok/s -11% 0.6 GB Whisper Transcription community 2026-04-08
🔢 GTE Large FP16 80 tok/s 80 tok/s +0% 0.9 GB Ollama editorial 2026-02-10
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 75 tok/s 45 tok/s +67% 0.6 GB LM Studio editorial 2026-03-20
Ternary Bonsai 4B Ternary Bonsai 4B Q2 56 tok/s 63 tok/s -11% 1.0 GB Ollama editorial 2026-03-14
SmolLM2 360M SmolLM2 360M FP16 55 tok/s 59 tok/s -7% 1.1 GB Ollama editorial 2026-04-19
🗣️ OuteTTS 0.3 500M FP16 48 tok/s 54 tok/s -11% 1.1 GB Piper editorial 2026-02-12
👁️ SmolVLM 500M FP16 45 tok/s 49 tok/s -8% 1.4 GB Xybrid CLI community 2026-03-25
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 44 tok/s 46 tok/s -4% 1.3 GB Xybrid CLI community 2026-03-26
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 43 tok/s 45 tok/s -4% 1.5 GB Xybrid CLI community 2026-01-18
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 41 tok/s 45 tok/s -9% 1.4 GB Xybrid CLI community 2026-04-07
Gemma 3 1B Gemma 3 1B Q4 38 tok/s 24 tok/s +58% 0.8 GB Ollama editorial 2026-03-20
🎙️ Distil-Whisper Large V3 FP16 37 tok/s 36 tok/s +3% 1.9 GB Xybrid CLI editorial 2026-03-01
🗣️ NeuTTS Air FP16 36 tok/s 36 tok/s +0% 1.8 GB Xybrid CLI community 2026-02-23
Whisper Medium Whisper Medium FP16 33 tok/s 36 tok/s -8% 1.7 GB Whisper Transcription community 2026-05-12
Ternary Bonsai 8B Ternary Bonsai 8B Q2 32 tok/s 34 tok/s -6% 1.9 GB Ollama editorial 2026-03-13
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 28 tok/s 30 tok/s -7% 2.1 GB Xybrid CLI community 2026-04-09
Bonsai Image 4B Bonsai Image 4B Q2 28 tok/s 30 tok/s -7% 2.0 GB Xybrid CLI community 2026-05-28
🎨 Stable Diffusion Turbo FP16 26 tok/s 26 tok/s +0% 2.3 GB Xybrid CLI community 2026-03-12
TinyLlama 1.1B TinyLlama 1.1B FP16 25 tok/s 24 tok/s +4% 2.6 GB Xybrid CLI community 2026-02-10
LFM2.5 1.2B LFM2.5 1.2B FP16 23 tok/s 23 tok/s +0% 3.0 GB Xybrid CLI editorial 2026-01-18
Gemma 3 1B Gemma 3 1B FP16 22 tok/s 24 tok/s -8% 2.8 GB Ollama editorial 2026-04-22
Llama 3.2 1B Llama 3.2 1B FP16 18 tok/s 20 tok/s -10% 3.0 GB Xybrid CLI community 2026-04-28
Whisper Large V3 Whisper Large V3 FP16 18 tok/s 17 tok/s +6% 3.6 GB Whisper Transcription community 2026-03-12
SmolLM2 1.7B SmolLM2 1.7B FP16 16 tok/s 16 tok/s +0% 3.9 GB Ollama editorial 2026-01-14
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 16 tok/s 17 tok/s -6% 4.1 GB Xybrid CLI community 2026-04-06
🗣️ Dia 1.6B FP16 16 tok/s 16 tok/s +0% 4.0 GB Xybrid CLI community 2026-02-24
StableLM 2 1.6B StableLM 2 1.6B FP16 15 tok/s 16 tok/s -6% 4.1 GB Ollama community 2026-05-23
🧠 DeepSeek R1 Distill 1.5B FP16 15 tok/s 16 tok/s -6% 3.9 GB Ollama community 2026-03-13
Qwen 3.5 2B Qwen 3.5 2B FP16 14 tok/s 13 tok/s +8% 4.9 GB Xybrid CLI community 2026-03-16
👁️ Moondream 2B FP16 14 tok/s 15 tok/s -7% 4.6 GB Ollama community 2026-03-13
Gemma 3n E2B Gemma 3n E2B Q8 11 tok/s 11 tok/s +0% 6.1 GB Ollama editorial 2026-02-23
Mistral Nemo 12B Mistral Nemo 12B Q3 11 tok/s 10 tok/s +10% 5.6 GB Ollama community 2026-04-07
Gemma 4 E2B Gemma 4 E2B FP16 11 tok/s 12 tok/s -8% 4.7 GB Xybrid CLI community 2026-03-28
Gemma 4 E4B Gemma 4 E4B Q8 11 tok/s 11 tok/s +0% 5.6 GB Ollama editorial 2026-05-08
Qwen 3.5 4B Qwen 3.5 4B Q8 11 tok/s 12 tok/s -8% 5.6 GB Ollama editorial 2026-04-22
Phi-4 Mini Phi-4 Mini Q8 11 tok/s 12 tok/s -8% 5.5 GB Ollama community 2026-02-23
👨‍💻 DeepSeek Coder 6.7B Q6 11 tok/s 10 tok/s +10% 6.2 GB Xybrid CLI community 2026-03-12
🎨 Stable Diffusion 3.5 Medium FP16 11 tok/s 12 tok/s -8% 5.6 GB Ollama community 2026-03-15
🎨 FLUX.1 Schnell Q3 11 tok/s 11 tok/s +0% 6.4 GB Ollama editorial 2026-01-21
Gemma 3 4B Gemma 3 4B Q8 10 tok/s 11 tok/s -9% 5.9 GB Ollama community 2026-02-11
Llama 3.1 8B Llama 3.1 8B Q6 10 tok/s 9 tok/s +11% 7.1 GB Xybrid CLI community 2026-04-07
Qwen 3.5 9B Qwen 3.5 9B Q5 10 tok/s 9 tok/s +11% 6.9 GB Ollama editorial 2026-01-06
🧠 DeepSeek R1 Distill 7B Q6 10 tok/s 9 tok/s +11% 6.2 GB Ollama community 2026-03-02
Qwen 2.5 7B Qwen 2.5 7B Q6 9 tok/s 9 tok/s +0% 7.1 GB Xybrid CLI community 2026-01-19
Gemma 3 12B Gemma 3 12B Q3 9 tok/s 10 tok/s -10% 6.2 GB Xybrid CLI community 2026-04-06
Mistral 7B Mistral 7B Q6 9 tok/s 9 tok/s +0% 7.5 GB Ollama editorial 2026-03-04
🧠 DeepSeek R1 Distill 8B Q6 9 tok/s 9 tok/s +0% 7.8 GB Ollama community 2026-03-16
🧠 Qwen3 8B Q6 9 tok/s 9 tok/s +0% 7.8 GB Ollama community 2026-01-22
👁️ LLaVA 1.6 7B Q6 9 tok/s 10 tok/s -10% 7.1 GB Ollama editorial 2026-05-27
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q6 9 tok/s 9 tok/s +0% 6.9 GB Ollama community 2026-04-12
Qwen 2.5 3B Qwen 2.5 3B FP16 8 tok/s 8 tok/s +0% 7.5 GB Xybrid CLI community 2026-01-21
Llama 3.2 3B Llama 3.2 3B FP16 8 tok/s 8 tok/s +0% 7.9 GB Xybrid CLI community 2026-01-19
Gemma 3n E4B Gemma 3n E4B Q6 8 tok/s 9 tok/s -11% 7.5 GB Xybrid CLI community 2026-01-19
LFM2.5 8B A1B LFM2.5 8B A1B Q6 8 tok/s 8 tok/s +0% 6.9 GB Ollama community 2026-05-25
Phi-4 Medium Phi-4 Medium Q3 8 tok/s 9 tok/s -11% 6.4 GB Xybrid CLI community 2026-02-01
👨‍💻 StarCoder2 3B FP16 8 tok/s 9 tok/s -11% 7.7 GB Xybrid CLI community 2026-02-23
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q6 8 tok/s 9 tok/s -11% 6.9 GB Xybrid CLI community 2026-01-16
🎨 SDXL Turbo FP16 8 tok/s 8 tok/s +0% 7.2 GB Ollama community 2026-01-03
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 7 tok/s 8 tok/s -12% 7.7 GB Xybrid CLI community 2026-05-14