Model Quant Measured Estimated RAM used App Source Date
🔢 all-MiniLM-L6-v2 FP16 220 tok/s 200 tok/s +10% 0.1 GB Ollama community 2026-03-02
🗣️ KittenTTS Mini FP16 201 tok/s 200 tok/s +1% 0.2 GB Xybrid CLI community 2026-02-28
🔢 BGE Small FP16 199 tok/s 200 tok/s +0% 0.1 GB Ollama community 2026-01-01
Whisper Tiny Whisper Tiny FP16 196 tok/s 200 tok/s -2% 0.1 GB Whisper Transcription community 2026-04-05
🗣️ KittenTTS Nano FP16 192 tok/s 200 tok/s -4% 0.1 GB Xybrid CLI community 2026-01-20
Wav2Vec2 Base Wav2Vec2 Base FP16 143 tok/s 139 tok/s +3% 0.3 GB Xybrid CLI community 2026-03-03
🔢 Nomic Embed Text FP16 114 tok/s 119 tok/s -4% 0.3 GB Xybrid CLI community 2026-01-19
SmolLM2 135M SmolLM2 135M FP16 111 tok/s 119 tok/s -7% 0.3 GB Jan community 2026-02-22
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 87 tok/s 84 tok/s +4% 0.5 GB Jan community 2026-04-22
🗣️ Kokoro 82M FP16 82 tok/s 89 tok/s -8% 0.4 GB Xybrid CLI community 2026-02-20
Whisper Small Whisper Small FP16 60 tok/s 65 tok/s -8% 0.6 GB Xybrid CLI editorial 2026-04-21
🔢 GTE Large FP16 51 tok/s 48 tok/s +6% 0.7 GB LM Studio community 2026-02-24
🗣️ OuteTTS 0.3 500M FP16 35 tok/s 32 tok/s +9% 1.2 GB Piper community 2026-02-23
SmolLM2 360M SmolLM2 360M FP16 34 tok/s 35 tok/s -3% 1.1 GB Ollama community 2026-04-21
Ternary Bonsai 4B Ternary Bonsai 4B Q2 33 tok/s 37 tok/s -11% 1.1 GB Jan community 2026-03-24
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 29 tok/s 27 tok/s +7% 1.4 GB Xybrid CLI community 2026-04-19
👁️ SmolVLM 500M FP16 29 tok/s 29 tok/s +0% 1.4 GB Jan community 2026-04-22
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 28 tok/s 28 tok/s +0% 1.5 GB Jan community 2026-04-19
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 24 tok/s 27 tok/s -11% 1.4 GB Jan community 2026-05-16
Ternary Bonsai 8B Ternary Bonsai 8B Q2 21 tok/s 20 tok/s +5% 1.8 GB LM Studio editorial 2026-04-07
Whisper Medium Whisper Medium FP16 21 tok/s 21 tok/s +0% 1.7 GB Xybrid CLI community 2026-01-03
Bonsai Image 4B Bonsai Image 4B Q2 20 tok/s 18 tok/s +11% 2.0 GB LM Studio editorial 2026-02-11
🎙️ Distil-Whisper Large V3 FP16 20 tok/s 21 tok/s -5% 1.6 GB Xybrid CLI community 2026-01-04
🗣️ NeuTTS Air FP16 19 tok/s 21 tok/s -10% 1.9 GB Piper community 2026-05-23
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 18 tok/s 18 tok/s +0% 2.3 GB LM Studio editorial 2026-02-24
Gemma 3 1B Gemma 3 1B FP16 15 tok/s 15 tok/s +0% 2.7 GB LM Studio community 2026-01-22
TinyLlama 1.1B TinyLlama 1.1B FP16 15 tok/s 15 tok/s +0% 2.5 GB Jan community 2026-04-06
🎨 Stable Diffusion Turbo FP16 15 tok/s 15 tok/s +0% 2.6 GB LM Studio editorial 2026-01-20
LFM2.5 1.2B LFM2.5 1.2B FP16 14 tok/s 14 tok/s +0% 2.8 GB Xybrid CLI community 2026-02-24
Whisper Tiny Whisper Tiny FP16 12 tok/s 200 tok/s -94% 0.1 GB Ollama editorial 2026-03-20
Llama 3.2 1B Llama 3.2 1B FP16 11 tok/s 12 tok/s -8% 3.5 GB LM Studio editorial 2026-01-28
Whisper Large V3 Whisper Large V3 FP16 11 tok/s 10 tok/s +10% 3.6 GB Whisper Transcription community 2026-03-12
StableLM 2 1.6B StableLM 2 1.6B FP16 10 tok/s 10 tok/s +0% 3.5 GB LM Studio community 2026-03-28
SmolLM2 1.7B SmolLM2 1.7B FP16 10 tok/s 9 tok/s +11% 3.8 GB Xybrid CLI editorial 2026-01-03
Qwen 2.5 3B Qwen 2.5 3B Q8 10 tok/s 9 tok/s +11% 3.9 GB Ollama community 2026-03-04
🧠 DeepSeek R1 Distill 1.5B FP16 10 tok/s 10 tok/s +0% 4.3 GB Jan community 2026-04-22
👨‍💻 StarCoder2 3B Q8 10 tok/s 10 tok/s +0% 3.7 GB LM Studio editorial 2026-05-08
Llama 3.2 3B Llama 3.2 3B Q8 9 tok/s 9 tok/s +0% 4.0 GB Ollama community 2026-02-10
Qwen 3.5 2B Qwen 3.5 2B FP16 9 tok/s 8 tok/s +13% 5.0 GB Xybrid CLI community 2026-05-24
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 9 tok/s 10 tok/s -10% 4.0 GB Ollama community 2026-02-23
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B Q8 9 tok/s 9 tok/s +0% 4.5 GB LM Studio editorial 2026-03-25
🗣️ Dia 1.6B FP16 9 tok/s 10 tok/s -10% 3.5 GB Piper community 2026-01-01
Qwen 2.5 0.5B Qwen 2.5 0.5B Q4 8 tok/s 27 tok/s -70% 0.4 GB Ollama editorial 2026-03-20
Gemma 3 4B Gemma 3 4B Q8 8 tok/s 7 tok/s +14% 5.4 GB Xybrid CLI community 2026-01-02
Gemma 4 E2B Gemma 4 E2B FP16 8 tok/s 7 tok/s +14% 5.4 GB Ollama community 2026-01-17
Qwen 3.5 4B Qwen 3.5 4B Q8 8 tok/s 7 tok/s +14% 5.3 GB Jan community 2026-02-11
👁️ Moondream 2B FP16 8 tok/s 9 tok/s -11% 4.1 GB Jan community 2026-03-10
🎨 SDXL Turbo Q8 8 tok/s 8 tok/s +0% 4.9 GB LM Studio editorial 2026-02-26
Gemma 3n E2B Gemma 3n E2B Q8 7 tok/s 7 tok/s +0% 6.2 GB Ollama editorial 2026-05-28
Phi-4 Mini Phi-4 Mini Q8 7 tok/s 7 tok/s +0% 4.9 GB LM Studio editorial 2026-01-15
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q5 7 tok/s 6 tok/s +17% 5.9 GB Xybrid CLI editorial 2026-02-07
Gemma 3 12B Gemma 3 12B Q3 6 tok/s 6 tok/s +0% 6.6 GB LM Studio editorial 2026-02-24
Mistral Nemo 12B Mistral Nemo 12B Q3 6 tok/s 6 tok/s +0% 6.6 GB LM Studio editorial 2026-01-03
Gemma 4 E4B Gemma 4 E4B Q8 6 tok/s 6 tok/s +0% 5.5 GB Xybrid CLI community 2026-04-05
Qwen 3.5 9B Qwen 3.5 9B Q4 6 tok/s 6 tok/s +0% 6.1 GB LM Studio editorial 2026-04-05
LFM2.5 8B A1B LFM2.5 8B A1B Q5 6 tok/s 6 tok/s +0% 6.3 GB Jan community 2026-01-05
Mistral 7B Mistral 7B Q6 6 tok/s 5 tok/s +20% 6.7 GB Ollama community 2026-03-04
🧠 DeepSeek R1 Distill 8B Q5 6 tok/s 6 tok/s +0% 6.9 GB Jan community 2026-05-24
🧠 Qwen3 8B Q5 6 tok/s 6 tok/s +0% 7.0 GB Jan community 2026-05-28
👨‍💻 DeepSeek Coder 6.7B Q6 6 tok/s 6 tok/s +0% 6.0 GB Jan community 2026-05-16
👁️ LLaVA 1.6 7B Q6 6 tok/s 6 tok/s +0% 6.0 GB Jan community 2026-02-07
🎨 Stable Diffusion 3.5 Medium FP16 6 tok/s 7 tok/s -14% 5.4 GB LM Studio community 2026-02-08
🎨 FLUX.1 Schnell Q3 6 tok/s 6 tok/s +0% 5.5 GB Ollama community 2026-01-01
Gemma 3n E4B Gemma 3n E4B Q5 5 tok/s 6 tok/s -17% 6.3 GB Xybrid CLI editorial 2026-05-05
Qwen 2.5 7B Qwen 2.5 7B Q6 5 tok/s 5 tok/s +0% 6.8 GB Jan community 2026-05-16
Llama 3.1 8B Llama 3.1 8B Q5 5 tok/s 6 tok/s -17% 6.5 GB Xybrid CLI community 2026-05-24
🧠 DeepSeek R1 Distill 7B Q6 5 tok/s 5 tok/s +0% 6.3 GB Ollama community 2026-01-01
Phi-4 Medium Phi-4 Medium Q3 5 tok/s 5 tok/s +0% 7.3 GB Jan community 2026-04-20
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q6 5 tok/s 5 tok/s +0% 6.4 GB Ollama community 2026-02-08