Model Quant Measured Estimated RAM used App Source Date
SmolLM2 135M SmolLM2 135M FP16 217 tok/s 200 tok/s +9% 0.3 GB Xybrid CLI community 2026-02-09
🔢 BGE Small FP16 215 tok/s 200 tok/s +8% 0.1 GB Ollama community 2026-01-08
🗣️ KittenTTS Mini FP16 209 tok/s 200 tok/s +5% 0.2 GB Xybrid CLI community 2026-03-13
🗣️ KittenTTS Nano FP16 208 tok/s 200 tok/s +4% 0.1 GB Xybrid CLI community 2026-02-10
Whisper Tiny Whisper Tiny FP16 207 tok/s 200 tok/s +4% 0.1 GB Xybrid CLI editorial 2026-05-09
🔢 all-MiniLM-L6-v2 FP16 193 tok/s 200 tok/s -4% 0.1 GB Ollama community 2026-02-07
Wav2Vec2 Base Wav2Vec2 Base FP16 185 tok/s 200 tok/s -7% 0.3 GB Xybrid CLI editorial 2026-05-27
🔢 Nomic Embed Text FP16 180 tok/s 200 tok/s -10% 0.3 GB Ollama editorial 2026-04-21
🗣️ Kokoro 82M FP16 161 tok/s 150 tok/s +7% 0.5 GB Xybrid CLI community 2026-01-02
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 145 tok/s 142 tok/s +2% 0.5 GB Xybrid CLI community 2026-05-24
Whisper Small Whisper Small FP16 116 tok/s 110 tok/s +5% 0.6 GB Whisper Transcription community 2026-02-11
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 82 tok/s 45 tok/s +82% 0.9 GB LM Studio community 2026-03-02
🔢 GTE Large FP16 76 tok/s 80 tok/s -5% 0.8 GB Xybrid CLI community 2026-01-22
SmolLM2 360M SmolLM2 360M FP16 65 tok/s 59 tok/s +10% 1.1 GB Ollama community 2026-02-24
🗣️ OuteTTS 0.3 500M FP16 58 tok/s 54 tok/s +7% 1.2 GB Piper community 2026-01-16
Ternary Bonsai 4B Ternary Bonsai 4B Q2 57 tok/s 63 tok/s -10% 1.1 GB Xybrid CLI community 2026-03-28
Gemma 3 1B Gemma 3 1B Q4 55 tok/s 24 tok/s +129% 0.9 GB Jan community 2026-03-03
👁️ SmolVLM 500M FP16 50 tok/s 49 tok/s +2% 1.4 GB Xybrid CLI community 2026-05-25
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 49 tok/s 45 tok/s +9% 1.5 GB Xybrid CLI community 2026-03-13
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 46 tok/s 45 tok/s +2% 1.4 GB Ollama community 2026-02-11
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 41 tok/s 46 tok/s -11% 1.3 GB Ollama editorial 2026-01-06
🗣️ NeuTTS Air FP16 40 tok/s 36 tok/s +11% 1.8 GB Xybrid CLI community 2026-04-20
🎙️ Distil-Whisper Large V3 FP16 40 tok/s 36 tok/s +11% 1.8 GB Whisper Transcription community 2026-04-22
Whisper Medium Whisper Medium FP16 33 tok/s 36 tok/s -8% 1.9 GB Xybrid CLI editorial 2026-05-23
Ternary Bonsai 8B Ternary Bonsai 8B Q2 31 tok/s 34 tok/s -9% 2.0 GB Xybrid CLI community 2026-02-22
🎨 Stable Diffusion Turbo FP16 28 tok/s 26 tok/s +8% 2.3 GB Ollama community 2026-04-08
Bonsai Image 4B Bonsai Image 4B Q2 28 tok/s 30 tok/s -7% 1.9 GB Xybrid CLI community 2026-02-22
Gemma 3 1B Gemma 3 1B FP16 27 tok/s 24 tok/s +13% 2.5 GB Ollama community 2026-03-03
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 27 tok/s 30 tok/s -10% 2.2 GB Xybrid CLI community 2026-04-18
TinyLlama 1.1B TinyLlama 1.1B FP16 26 tok/s 24 tok/s +8% 2.3 GB Ollama community 2026-03-02
LFM2.5 1.2B LFM2.5 1.2B FP16 25 tok/s 23 tok/s +9% 2.8 GB Xybrid CLI community 2026-02-10
Llama 3.2 1B Llama 3.2 1B FP16 20 tok/s 20 tok/s +0% 3.0 GB Ollama community 2026-01-28
🧠 DeepSeek R1 Distill 1.5B FP16 17 tok/s 16 tok/s +6% 3.9 GB Ollama community 2026-05-11
🗣️ Dia 1.6B FP16 17 tok/s 16 tok/s +6% 4.0 GB Xybrid CLI community 2026-04-20
Whisper Large V3 Whisper Large V3 FP16 17 tok/s 17 tok/s +0% 4.0 GB Xybrid CLI editorial 2026-02-27
StableLM 2 1.6B StableLM 2 1.6B FP16 16 tok/s 16 tok/s +0% 3.9 GB Xybrid CLI community 2026-01-18
SmolLM2 1.7B SmolLM2 1.7B FP16 15 tok/s 16 tok/s -6% 4.2 GB Ollama community 2026-04-22
Qwen 2.5 3B Qwen 2.5 3B Q8 15 tok/s 15 tok/s +0% 3.9 GB Ollama community 2026-02-10
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 15 tok/s 17 tok/s -12% 3.7 GB Ollama editorial 2026-03-15
🎨 SDXL Turbo Q8 15 tok/s 14 tok/s +7% 4.9 GB Ollama editorial 2026-03-28
Llama 3.2 3B Llama 3.2 3B Q8 14 tok/s 15 tok/s -7% 4.5 GB Ollama community 2026-05-23
👨‍💻 StarCoder2 3B Q8 14 tok/s 16 tok/s -12% 3.7 GB Ollama editorial 2026-02-10
👁️ Moondream 2B FP16 14 tok/s 15 tok/s -7% 4.8 GB Xybrid CLI community 2026-03-28
🎨 FLUX.1 Schnell Q2 14 tok/s 13 tok/s +8% 4.8 GB Xybrid CLI community 2026-03-14
Qwen 2.5 7B Qwen 2.5 7B Q4 13 tok/s 12 tok/s +8% 5.4 GB Xybrid CLI community 2026-04-17
Llama 3.1 8B Llama 3.1 8B Q4 13 tok/s 12 tok/s +8% 5.3 GB Xybrid CLI community 2026-03-14
Gemma 4 E2B Gemma 4 E2B FP16 13 tok/s 12 tok/s +8% 5.1 GB Ollama editorial 2026-02-10
Qwen 3.5 2B Qwen 3.5 2B FP16 13 tok/s 13 tok/s +0% 5.2 GB Ollama editorial 2026-02-26
Qwen 3.5 4B Qwen 3.5 4B Q8 13 tok/s 12 tok/s +8% 4.9 GB Ollama community 2026-03-04
Phi-4 Mini Phi-4 Mini Q8 13 tok/s 12 tok/s +8% 4.7 GB Xybrid CLI community 2026-01-06
🧠 DeepSeek R1 Distill 7B Q4 13 tok/s 12 tok/s +8% 5.2 GB Xybrid CLI community 2026-03-12
🧠 DeepSeek R1 Distill 8B Q4 13 tok/s 12 tok/s +8% 5.6 GB Ollama community 2026-01-14
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q8 13 tok/s 15 tok/s -13% 4.3 GB Ollama community 2026-04-21
👨‍💻 DeepSeek Coder 6.7B Q5 13 tok/s 12 tok/s +8% 5.7 GB Ollama editorial 2026-02-27
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q4 13 tok/s 12 tok/s +8% 5.3 GB Xybrid CLI community 2026-05-24
🎨 Stable Diffusion 3.5 Medium FP16 13 tok/s 12 tok/s +8% 5.5 GB Xybrid CLI community 2026-01-18
Gemma 3 12B Gemma 3 12B Q2 12 tok/s 13 tok/s -8% 5.1 GB Ollama editorial 2026-04-21
Mistral Nemo 12B Mistral Nemo 12B Q2 12 tok/s 13 tok/s -8% 4.2 GB Xybrid CLI community 2026-05-23
Qwen 3.5 9B Qwen 3.5 9B Q3 12 tok/s 13 tok/s -8% 5.2 GB Xybrid CLI community 2026-02-23
LFM2.5 8B A1B LFM2.5 8B A1B Q4 12 tok/s 11 tok/s +9% 5.3 GB Ollama community 2026-03-03
👁️ LLaVA 1.6 7B Q5 12 tok/s 11 tok/s +9% 6.0 GB Ollama editorial 2026-03-02
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q4 12 tok/s 12 tok/s +0% 5.5 GB Xybrid CLI community 2026-04-21
Gemma 3n E4B Gemma 3n E4B Q5 11 tok/s 11 tok/s +0% 5.3 GB Ollama community 2026-02-08
Gemma 4 E4B Gemma 4 E4B Q8 11 tok/s 11 tok/s +0% 6.2 GB Xybrid CLI community 2026-04-23
🧠 Qwen3 8B Q4 11 tok/s 11 tok/s +0% 5.2 GB Ollama editorial 2026-05-11
Gemma 3n E2B Gemma 3n E2B Q8 10 tok/s 11 tok/s -9% 5.1 GB Ollama community 2026-05-24
Gemma 3 4B Gemma 3 4B Q8 10 tok/s 11 tok/s -9% 6.1 GB Ollama community 2026-01-16
Mistral 7B Mistral 7B Q5 10 tok/s 11 tok/s -9% 6.1 GB Ollama community 2026-01-28
Phi-4 Medium Phi-4 Medium Q2 10 tok/s 11 tok/s -9% 5.9 GB Xybrid CLI community 2026-03-26