Model Quant Measured Estimated RAM used App Source Date
🔢 all-MiniLM-L6-v2 FP16 217 tok/s 200 tok/s +9% 0.1 GB Jan community 2026-01-25
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 215 tok/s 200 tok/s +8% 0.4 GB Ollama community 2026-04-08
🔢 BGE Small FP16 215 tok/s 200 tok/s +8% 0.1 GB Xybrid CLI community 2026-01-02
🔢 Nomic Embed Text FP16 206 tok/s 200 tok/s +3% 0.4 GB Jan community 2026-04-21
🗣️ Kokoro 82M FP16 197 tok/s 200 tok/s -1% 0.5 GB Xybrid CLI editorial 2026-05-16
SmolLM2 135M SmolLM2 135M FP16 192 tok/s 200 tok/s -4% 0.3 GB Xybrid CLI community 2026-01-20
🗣️ KittenTTS Mini FP16 188 tok/s 200 tok/s -6% 0.2 GB Xybrid CLI community 2026-04-04
Wav2Vec2 Base Wav2Vec2 Base FP16 186 tok/s 200 tok/s -7% 0.3 GB Xybrid CLI community 2026-03-13
Whisper Tiny Whisper Tiny FP16 183 tok/s 200 tok/s -8% 0.1 GB Whisper Transcription community 2026-04-08
🗣️ KittenTTS Nano FP16 177 tok/s 200 tok/s -11% 0.1 GB Xybrid CLI community 2026-03-07
Whisper Small Whisper Small FP16 159 tok/s 180 tok/s -12% 0.5 GB Xybrid CLI community 2026-03-13
Qwen 2.5 0.5B Qwen 2.5 0.5B Q8 130 tok/s 73 tok/s +78% 0.9 GB Ollama community 2026-03-08
🔢 GTE Large FP16 128 tok/s 131 tok/s -2% 0.8 GB Jan community 2026-04-18
Ternary Bonsai 4B Ternary Bonsai 4B Q2 112 tok/s 102 tok/s +10% 1.0 GB Xybrid CLI community 2026-04-22
SmolLM2 360M SmolLM2 360M FP16 97 tok/s 96 tok/s +1% 1.0 GB Ollama community 2026-02-10
👁️ SmolVLM 500M FP16 86 tok/s 80 tok/s +8% 1.3 GB Xybrid CLI community 2026-03-14
🗣️ OuteTTS 0.3 500M FP16 85 tok/s 88 tok/s -3% 1.1 GB Piper community 2026-01-04
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 79 tok/s 76 tok/s +4% 1.5 GB LM Studio editorial 2026-03-01
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 78 tok/s 73 tok/s +7% 1.5 GB Xybrid CLI community 2026-02-07
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 71 tok/s 73 tok/s -3% 1.5 GB Jan community 2026-04-18
Whisper Medium Whisper Medium FP16 65 tok/s 59 tok/s +10% 1.8 GB Xybrid CLI community 2026-01-13
🎙️ Distil-Whisper Large V3 FP16 64 tok/s 59 tok/s +8% 1.6 GB Whisper Transcription community 2026-02-08
🗣️ NeuTTS Air FP16 53 tok/s 59 tok/s -10% 1.7 GB Piper editorial 2026-02-09
Llama 3.2 1B Llama 3.2 1B Q4 52 tok/s 33 tok/s +58% 1.0 GB Ollama community 2026-03-09
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 50 tok/s 49 tok/s +2% 2.3 GB Jan community 2026-05-27
Ternary Bonsai 8B Ternary Bonsai 8B Q2 48 tok/s 55 tok/s -13% 1.8 GB Jan community 2026-04-07
Bonsai Image 4B Bonsai Image 4B Q2 48 tok/s 49 tok/s -2% 1.9 GB Ollama community 2026-01-06
Gemma 3 1B Gemma 3 1B FP16 45 tok/s 40 tok/s +13% 2.4 GB LM Studio community 2026-01-04
TinyLlama 1.1B TinyLlama 1.1B FP16 41 tok/s 40 tok/s +3% 2.8 GB Jan community 2026-05-26
LFM2.5 1.2B LFM2.5 1.2B FP16 39 tok/s 38 tok/s +3% 2.7 GB LM Studio editorial 2026-01-13
🎨 Stable Diffusion Turbo FP16 39 tok/s 42 tok/s -7% 2.5 GB LM Studio community 2026-02-09
Llama 3.2 1B Llama 3.2 1B FP16 34 tok/s 33 tok/s +3% 3.0 GB LM Studio editorial 2026-01-16
StableLM 2 1.6B StableLM 2 1.6B FP16 30 tok/s 27 tok/s +11% 3.6 GB Xybrid CLI community 2026-01-02
🧠 DeepSeek R1 Distill 1.5B FP16 29 tok/s 27 tok/s +7% 3.8 GB Jan community 2026-03-15
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 29 tok/s 28 tok/s +4% 4.0 GB LM Studio editorial 2026-03-03
🗣️ Dia 1.6B FP16 29 tok/s 27 tok/s +7% 4.3 GB Xybrid CLI community 2026-05-26
SmolLM2 1.7B SmolLM2 1.7B FP16 28 tok/s 26 tok/s +8% 4.1 GB Jan community 2026-02-10
Whisper Large V3 Whisper Large V3 FP16 28 tok/s 28 tok/s +0% 3.9 GB Whisper Transcription community 2026-05-25
👁️ Moondream 2B FP16 23 tok/s 24 tok/s -4% 4.7 GB LM Studio editorial 2026-01-02
Qwen 3.5 2B Qwen 3.5 2B FP16 22 tok/s 21 tok/s +5% 5.3 GB Jan community 2026-01-01
🎨 Stable Diffusion 3.5 Medium FP16 19 tok/s 19 tok/s +0% 5.4 GB Jan community 2026-02-07
Gemma 4 E2B Gemma 4 E2B FP16 18 tok/s 20 tok/s -10% 5.6 GB LM Studio editorial 2026-01-02
🎨 SDXL Turbo FP16 16 tok/s 14 tok/s +14% 7.4 GB Xybrid CLI editorial 2026-02-09
Qwen 2.5 3B Qwen 2.5 3B FP16 15 tok/s 14 tok/s +7% 7.5 GB Ollama community 2026-01-14
👨‍💻 StarCoder2 3B FP16 14 tok/s 14 tok/s +0% 7.3 GB Jan community 2026-02-07
Gemma 3n E4B Gemma 3n E4B Q8 13 tok/s 12 tok/s +8% 8.9 GB Ollama community 2026-01-15
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 13 tok/s 14 tok/s -7% 7.7 GB Ollama community 2026-04-20
👁️ LLaVA 1.6 7B Q8 13 tok/s 12 tok/s +8% 8.6 GB LM Studio editorial 2026-02-10
Llama 3.2 3B Llama 3.2 3B FP16 12 tok/s 13 tok/s -8% 7.8 GB LM Studio community 2026-03-15
🧠 DeepSeek R1 Distill 7B Q8 12 tok/s 11 tok/s +9% 9.4 GB Ollama community 2026-05-11
Mistral 7B Mistral 7B Q8 12 tok/s 11 tok/s +9% 10.1 GB Ollama community 2026-02-21
👨‍💻 DeepSeek Coder 6.7B Q8 12 tok/s 12 tok/s +0% 8.9 GB Jan community 2026-05-01
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q8 12 tok/s 11 tok/s +9% 9.2 GB Ollama editorial 2026-05-11
Llama 3.1 8B Llama 3.1 8B Q8 11 tok/s 10 tok/s +10% 9.3 GB Xybrid CLI community 2026-01-05
Qwen 3.5 4B Qwen 3.5 4B FP16 11 tok/s 11 tok/s +0% 10.3 GB Jan community 2026-04-20
🧠 Qwen3 8B Q8 11 tok/s 10 tok/s +10% 10.7 GB Xybrid CLI community 2026-05-23
Gemma 3n E2B Gemma 3n E2B FP16 10 tok/s 10 tok/s +0% 9.9 GB LM Studio editorial 2026-05-11
Qwen 2.5 7B Qwen 2.5 7B Q8 10 tok/s 11 tok/s -9% 9.7 GB Ollama community 2026-04-19
Qwen 3.5 9B Qwen 3.5 9B Q8 10 tok/s 9 tok/s +11% 12.0 GB Xybrid CLI community 2026-04-18
Phi-4 Mini Phi-4 Mini FP16 10 tok/s 11 tok/s -9% 9.5 GB Xybrid CLI community 2026-05-23
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q8 10 tok/s 10 tok/s +0% 9.1 GB Ollama community 2026-02-06
Gemma 3 4B Gemma 3 4B FP16 9 tok/s 10 tok/s -10% 11.4 GB LM Studio editorial 2026-04-20
Mistral Nemo 12B Mistral Nemo 12B Q6 9 tok/s 9 tok/s +0% 12.0 GB Xybrid CLI community 2026-05-27
Gemma 4 E4B Gemma 4 E4B FP16 9 tok/s 10 tok/s -10% 11.3 GB Xybrid CLI editorial 2026-03-17
Gemma 4 31B Gemma 4 31B Q2 9 tok/s 8 tok/s +13% 13.3 GB Xybrid CLI community 2026-02-08
LFM2.5 8B A1B LFM2.5 8B A1B Q8 9 tok/s 10 tok/s -10% 11.0 GB Jan community 2026-04-02
🧠 DeepSeek R1 Distill 8B Q8 9 tok/s 10 tok/s -10% 10.8 GB Ollama editorial 2026-05-26
🎨 FLUX.1 Schnell Q6 9 tok/s 9 tok/s +0% 11.6 GB Jan community 2026-04-19
Gemma 3 12B Gemma 3 12B Q6 8 tok/s 9 tok/s -11% 11.0 GB LM Studio editorial 2026-03-15
Gemma 4 26B A4B Gemma 4 26B A4B Q2 8 tok/s 9 tok/s -11% 11.5 GB Ollama editorial 2026-03-12
Phi-4 Medium Phi-4 Medium Q6 8 tok/s 8 tok/s +0% 12.6 GB Jan community 2026-05-11
👨‍💻 Laguna XS.2 Q2 8 tok/s 8 tok/s +0% 13.7 GB Ollama community 2026-04-22
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q2 7 tok/s 7 tok/s +0% 14.3 GB Xybrid CLI community 2026-01-20