SmolLM2 135M | Q8 | 246 tok/s | 200 tok/s
+23%
| 0.2 GB | LM Studio | community | 2026-02-10 |
Whisper Tiny | Q8 | 238 tok/s | 200 tok/s
+19%
| 0.1 GB | MacWhisper | editorial | 2026-05-12 |
| 🔢 Nomic Embed Text | Q8 | 235 tok/s | 200 tok/s
+18%
| 0.2 GB | Jan | community | 2026-03-16 |
Qwen 2.5 0.5B | Q8 | 234 tok/s | 200 tok/s
+17%
| 0.8 GB | Jan | community | 2026-03-13 |
| 🔢 GTE Large | Q8 | 234 tok/s | 200 tok/s
+17%
| 0.4 GB | Jan | community | 2026-02-07 |
SmolLM2 135M | FP16 | 223 tok/s | 200 tok/s
+12%
| 0.3 GB | Ollama | community | 2026-03-04 |
SmolLM2 360M | Q8 | 223 tok/s | 200 tok/s
+12%
| 0.7 GB | LM Studio | editorial | 2026-05-10 |
| 🗣️ Kokoro 82M | Q8 | 222 tok/s | 200 tok/s
+11%
| 0.3 GB | Xybrid CLI | community | 2026-04-04 |
Whisper Small | Q8 | 222 tok/s | 200 tok/s
+11%
| 0.3 GB | Xybrid CLI | editorial | 2026-02-23 |
Bonsai 8B (1-bit) | Q1 | 221 tok/s | 200 tok/s
+11%
| 1.3 GB | Ollama | community | 2026-03-02 |
Ternary Bonsai 1.7B | Q2 | 221 tok/s | 200 tok/s
+11%
| 0.4 GB | Xybrid CLI | editorial | 2026-01-03 |
| 🔢 all-MiniLM-L6-v2 | Q8 | 220 tok/s | 200 tok/s
+10%
| 0.1 GB | Xybrid CLI | editorial | 2026-01-19 |
SmolLM2 360M | FP16 | 218 tok/s | 200 tok/s
+9%
| 1.1 GB | Xybrid CLI | community | 2026-03-12 |
| 🔢 BGE Small | FP16 | 218 tok/s | 200 tok/s
+9%
| 0.1 GB | Xybrid CLI | editorial | 2026-02-10 |
| 🗣️ KittenTTS Mini | Q8 | 217 tok/s | 200 tok/s
+9%
| 0.1 GB | Xybrid CLI | community | 2026-03-14 |
| 🔢 Nomic Embed Text | FP16 | 216 tok/s | 200 tok/s
+8%
| 0.3 GB | Ollama | community | 2026-01-17 |
Qwen 2.5 Coder 0.5B | FP16 | 215 tok/s | 200 tok/s
+8%
| 1.4 GB | Ollama | community | 2026-02-19 |
| 🗣️ NeuTTS Air | Q8 | 214 tok/s | 182 tok/s
+18%
| 0.9 GB | Xybrid CLI | community | 2026-02-08 |
| 🔢 BGE Small | Q8 | 212 tok/s | 200 tok/s
+6%
| 0.1 GB | Jan | community | 2026-05-12 |
| 🗣️ KittenTTS Mini | FP16 | 211 tok/s | 200 tok/s
+6%
| 0.2 GB | Xybrid CLI | community | 2026-05-28 |
Qwen 2.5 Coder 0.5B | Q8 | 210 tok/s | 200 tok/s
+5%
| 0.9 GB | LM Studio | editorial | 2026-05-23 |
| 🗣️ KittenTTS Nano | Q8 | 209 tok/s | 200 tok/s
+5%
| 0.1 GB | Piper | community | 2026-05-28 |
Qwen 2.5 0.5B | FP16 | 208 tok/s | 200 tok/s
+4%
| 1.3 GB | Xybrid CLI | community | 2026-05-26 |
Wav2Vec2 Base | Q8 | 208 tok/s | 200 tok/s
+4%
| 0.2 GB | MacWhisper | editorial | 2026-04-21 |
Whisper Small | FP16 | 207 tok/s | 200 tok/s
+4%
| 0.6 GB | MacWhisper | editorial | 2026-05-09 |
| 🔢 all-MiniLM-L6-v2 | FP16 | 203 tok/s | 200 tok/s
+2%
| 0.1 GB | Jan | community | 2026-04-20 |
| 🗣️ KittenTTS Nano | FP16 | 203 tok/s | 200 tok/s
+2%
| 0.1 GB | Piper | community | 2026-04-14 |
Whisper Tiny | FP16 | 203 tok/s | 200 tok/s
+2%
| 0.1 GB | MacWhisper | editorial | 2026-02-26 |
| 👁️ SmolVLM 500M | Q8 | 203 tok/s | 200 tok/s
+2%
| 0.8 GB | Jan | community | 2026-03-06 |
Bonsai 8B (1-bit) | Q1 | 202 tok/s | 200 tok/s
+1%
| 1.5 GB | Jan | community | 2026-05-28 |
| 🗣️ OuteTTS 0.3 500M | Q8 | 201 tok/s | 200 tok/s
+1%
| 0.6 GB | Piper | editorial | 2026-03-15 |
Ternary Bonsai 4B | Q2 | 199 tok/s | 200 tok/s
+0%
| 1.1 GB | Jan | community | 2026-04-18 |
Whisper Medium | Q8 | 199 tok/s | 182 tok/s
+9%
| 1.0 GB | Xybrid CLI | community | 2026-02-24 |
Ternary Bonsai 4B | Q2 | 193 tok/s | 200 tok/s
-4%
| 1.1 GB | Xybrid CLI | community | 2026-01-17 |
| 👁️ SmolVLM 500M | FP16 | 191 tok/s | 200 tok/s
-4%
| 1.4 GB | Ollama | editorial | 2026-02-06 |
| 🔢 GTE Large | FP16 | 190 tok/s | 200 tok/s
-5%
| 0.7 GB | LM Studio | community | 2026-01-14 |
| 🗣️ Kokoro 82M | FP16 | 189 tok/s | 200 tok/s
-5%
| 0.4 GB | Xybrid CLI | community | 2026-01-18 |
| 🎙️ Distil-Whisper Large V3 | Q8 | 189 tok/s | 182 tok/s
+4%
| 1.0 GB | Xybrid CLI | community | 2026-05-16 |
Ternary Bonsai 1.7B | Q2 | 184 tok/s | 200 tok/s
-8%
| 0.4 GB | Jan | community | 2026-05-12 |
| 🗣️ OuteTTS 0.3 500M | FP16 | 183 tok/s | 200 tok/s
-8%
| 1.2 GB | Xybrid CLI | community | 2026-04-08 |
Wav2Vec2 Base | FP16 | 182 tok/s | 200 tok/s
-9%
| 0.3 GB | Xybrid CLI | community | 2026-03-28 |
| 🎙️ Distil-Whisper Large V3 | FP16 | 177 tok/s | 182 tok/s
-3%
| 1.6 GB | Xybrid CLI | community | 2026-04-02 |
| 🗣️ NeuTTS Air | FP16 | 174 tok/s | 182 tok/s
-4%
| 1.6 GB | Xybrid CLI | community | 2026-04-05 |
Bonsai Image 4B | Q1 | 174 tok/s | 152 tok/s
+14%
| 1.5 GB | Jan | community | 2026-01-01 |
Whisper Medium | FP16 | 170 tok/s | 182 tok/s
-7%
| 1.8 GB | MacWhisper | community | 2026-03-16 |
Bonsai Image 4B | Q2 | 169 tok/s | 152 tok/s
+11%
| 2.0 GB | Ollama | community | 2026-03-04 |
Ternary Bonsai 8B | Q2 | 161 tok/s | 171 tok/s
-6%
| 2.0 GB | LM Studio | editorial | 2026-01-04 |
Ternary Bonsai 8B | Q2 | 153 tok/s | 171 tok/s
-11%
| 2.0 GB | Ollama | community | 2026-02-24 |
Qwen 3.5 0.8B | Q8 | 153 tok/s | 152 tok/s
+1%
| 1.0 GB | LM Studio | community | 2026-04-21 |
TinyLlama 1.1B | Q8 | 143 tok/s | 124 tok/s
+15%
| 1.3 GB | Jan | community | 2026-02-08 |
Qwen 3.5 0.8B | FP16 | 142 tok/s | 152 tok/s
-7%
| 1.9 GB | Jan | community | 2026-02-22 |
Gemma 3 1B | Q8 | 142 tok/s | 124 tok/s
+15%
| 1.4 GB | Jan | community | 2026-03-13 |
| 🎨 Stable Diffusion Turbo | Q8 | 132 tok/s | 130 tok/s
+2%
| 1.4 GB | Jan | community | 2026-05-16 |
Gemma 3 1B | FP16 | 130 tok/s | 124 tok/s
+5%
| 2.4 GB | LM Studio | community | 2026-01-13 |
LFM2.5 1.2B | Q8 | 129 tok/s | 117 tok/s
+10%
| 1.6 GB | Xybrid CLI | editorial | 2026-02-22 |
TinyLlama 1.1B | FP16 | 122 tok/s | 124 tok/s
-2%
| 2.4 GB | Xybrid CLI | editorial | 2026-03-28 |
| 🎨 Stable Diffusion Turbo | FP16 | 122 tok/s | 130 tok/s
-6%
| 2.5 GB | Ollama | community | 2026-03-17 |
LFM2.5 1.2B | FP16 | 120 tok/s | 117 tok/s
+3%
| 2.7 GB | LM Studio | editorial | 2026-05-08 |
Llama 3.2 1B | Q8 | 107 tok/s | 101 tok/s
+6%
| 1.8 GB | Jan | community | 2026-01-17 |
Phi-4 Mini | Q5 | 105 tok/s | 35 tok/s
+200%
| 2.9 GB | Ollama | editorial | 2026-02-15 |
Llama 3.2 1B | FP16 | 100 tok/s | 101 tok/s
-1%
| 3.0 GB | Xybrid CLI | editorial | 2026-04-03 |
| 🧠 DeepSeek R1 Distill 1.5B | Q8 | 99 tok/s | 83 tok/s
+19%
| 1.9 GB | Xybrid CLI | community | 2026-01-06 |
SmolLM2 1.7B | Q8 | 94 tok/s | 80 tok/s
+18%
| 2.0 GB | Ollama | editorial | 2026-05-11 |
Qwen 2.5 Coder 1.5B | Q8 | 93 tok/s | 85 tok/s
+9%
| 2.0 GB | Ollama | community | 2026-03-15 |
StableLM 2 1.6B | Q8 | 89 tok/s | 83 tok/s
+7%
| 2.3 GB | Ollama | editorial | 2026-01-06 |
| 🗣️ Dia 1.6B | Q8 | 88 tok/s | 83 tok/s
+6%
| 2.0 GB | Xybrid CLI | community | 2026-03-14 |
Whisper Large V3 | Q8 | 88 tok/s | 88 tok/s
+0%
| 2.0 GB | Xybrid CLI | editorial | 2026-05-23 |
Whisper Large V3 | FP16 | 86 tok/s | 88 tok/s
-2%
| 3.7 GB | Xybrid CLI | community | 2026-04-18 |
| 👁️ Moondream 2B | Q8 | 86 tok/s | 74 tok/s
+16%
| 2.2 GB | LM Studio | editorial | 2026-01-15 |
| 🗣️ Dia 1.6B | FP16 | 82 tok/s | 83 tok/s
-1%
| 3.7 GB | Xybrid CLI | editorial | 2026-04-06 |
SmolLM2 1.7B | FP16 | 81 tok/s | 80 tok/s
+1%
| 4.2 GB | Xybrid CLI | community | 2026-02-25 |
Qwen 2.5 Coder 1.5B | FP16 | 80 tok/s | 85 tok/s
-6%
| 3.9 GB | Xybrid CLI | community | 2026-05-14 |
Llama 3.2 3B | Q8 | 78 tok/s | 41 tok/s
+90%
| 3.8 GB | LM Studio | editorial | 2026-02-18 |
| 👁️ Moondream 2B | FP16 | 78 tok/s | 74 tok/s
+5%
| 4.4 GB | Jan | community | 2026-02-08 |
Qwen 3.5 2B | Q8 | 78 tok/s | 65 tok/s
+20%
| 3.0 GB | Ollama | editorial | 2026-03-01 |
| 🧠 DeepSeek R1 Distill 1.5B | FP16 | 76 tok/s | 83 tok/s
-8%
| 3.8 GB | Jan | community | 2026-04-08 |
StableLM 2 1.6B | FP16 | 75 tok/s | 83 tok/s
-10%
| 4.2 GB | Jan | community | 2026-03-25 |
Mistral 7B | Q4 | 71 tok/s | 19 tok/s
+274%
| 4.3 GB | LM Studio | editorial | 2026-02-15 |
Gemma 4 E2B | Q8 | 70 tok/s | 61 tok/s
+15%
| 3.2 GB | Jan | community | 2026-04-22 |
| 🎨 Stable Diffusion 3.5 Medium | Q8 | 69 tok/s | 59 tok/s
+17%
| 3.2 GB | LM Studio | community | 2026-01-13 |
Qwen 3.5 2B | FP16 | 67 tok/s | 65 tok/s
+3%
| 5.4 GB | Jan | community | 2026-04-21 |
Gemma 4 E2B | FP16 | 66 tok/s | 61 tok/s
+8%
| 4.7 GB | LM Studio | community | 2026-03-21 |
| 🎨 Stable Diffusion 3.5 Medium | FP16 | 65 tok/s | 59 tok/s
+10%
| 5.5 GB | Xybrid CLI | community | 2026-04-22 |
Qwen 2.5 7B | Q4 | 64 tok/s | 18 tok/s
+256%
| 4.6 GB | Ollama | community | 2026-03-01 |
| 👨💻 StarCoder2 3B | Q8 | 55 tok/s | 44 tok/s
+25%
| 3.6 GB | Xybrid CLI | community | 2026-02-09 |
Qwen 2.5 3B | Q8 | 52 tok/s | 43 tok/s
+21%
| 3.7 GB | Ollama | community | 2026-03-28 |
Qwen 2.5 Coder 3B | Q8 | 52 tok/s | 43 tok/s
+21%
| 4.3 GB | Xybrid CLI | community | 2026-04-18 |
| 👨💻 StarCoder2 3B | FP16 | 47 tok/s | 44 tok/s
+7%
| 6.8 GB | Ollama | community | 2026-01-08 |
Llama 3.2 3B | Q8 | 45 tok/s | 41 tok/s
+10%
| 4.5 GB | Xybrid CLI | community | 2026-01-18 |
Qwen 2.5 3B | FP16 | 43 tok/s | 43 tok/s
+0%
| 8.1 GB | Jan | community | 2026-05-26 |
| 🎨 SDXL Turbo | Q8 | 43 tok/s | 42 tok/s
+2%
| 4.5 GB | Jan | community | 2026-05-11 |
Llama 3.2 3B | FP16 | 41 tok/s | 41 tok/s
+0%
| 8.2 GB | Jan | community | 2026-04-19 |
Gemma 3 12B | Q4 | 40 tok/s | 11 tok/s
+264%
| 7.3 GB | LM Studio | editorial | 2026-03-05 |
Qwen 2.5 Coder 3B | FP16 | 40 tok/s | 43 tok/s
-7%
| 7.4 GB | Ollama | editorial | 2026-03-13 |
| 🎨 SDXL Turbo | FP16 | 40 tok/s | 42 tok/s
-5%
| 7.6 GB | Ollama | community | 2026-03-12 |
Phi-4 Mini | Q8 | 40 tok/s | 35 tok/s
+14%
| 5.7 GB | Jan | community | 2026-01-01 |
Phi-4 Mini | FP16 | 39 tok/s | 35 tok/s
+11%
| 8.6 GB | Ollama | community | 2026-03-04 |
Qwen 3.5 4B | Q8 | 36 tok/s | 33 tok/s
+9%
| 5.3 GB | Xybrid CLI | community | 2026-05-16 |
Gemma 4 E4B | Q8 | 35 tok/s | 30 tok/s
+17%
| 5.9 GB | LM Studio | community | 2026-05-11 |
Gemma 3n E2B | Q8 | 34 tok/s | 31 tok/s
+10%
| 5.1 GB | Ollama | community | 2026-01-04 |
Gemma 3 4B | Q8 | 32 tok/s | 31 tok/s
+3%
| 5.8 GB | Ollama | community | 2026-02-11 |
Gemma 4 E4B | FP16 | 30 tok/s | 30 tok/s
+0%
| 11.5 GB | LM Studio | editorial | 2026-02-26 |
Gemma 3n E2B | FP16 | 29 tok/s | 31 tok/s
-6%
| 9.5 GB | Jan | community | 2026-03-24 |
Qwen 3.5 4B | FP16 | 29 tok/s | 33 tok/s
-12%
| 9.4 GB | LM Studio | editorial | 2026-03-13 |
Gemma 3 4B | FP16 | 28 tok/s | 31 tok/s
-10%
| 11.0 GB | LM Studio | community | 2026-05-25 |
Gemma 3n E4B | Q8 | 24 tok/s | 20 tok/s
+20%
| 8.4 GB | Jan | community | 2026-02-09 |
| 👨💻 DeepSeek Coder 6.7B | Q8 | 24 tok/s | 20 tok/s
+20%
| 8.4 GB | Jan | community | 2026-03-17 |
Qwen 2.5 7B | Q8 | 22 tok/s | 18 tok/s
+22%
| 8.8 GB | Ollama | community | 2026-04-08 |
| 🧠 DeepSeek R1 Distill 7B | Q8 | 22 tok/s | 18 tok/s
+22%
| 8.9 GB | Ollama | community | 2026-04-08 |
| 👁️ LLaVA 1.6 7B | Q8 | 22 tok/s | 19 tok/s
+16%
| 9.4 GB | LM Studio | editorial | 2026-02-23 |
Mistral 7B | Q8 | 21 tok/s | 19 tok/s
+11%
| 9.7 GB | LM Studio | community | 2026-01-20 |
Qwen 2.5 Coder 7B | Q8 | 21 tok/s | 18 tok/s
+17%
| 9.5 GB | Jan | community | 2026-02-07 |
| 🧠 DeepSeek R1 Distill 7B | FP16 | 20 tok/s | 18 tok/s
+11%
| 17.0 GB | Xybrid CLI | community | 2026-02-09 |
Llama 3.1 8B | Q8 | 20 tok/s | 17 tok/s
+18%
| 8.9 GB | Ollama | community | 2026-03-02 |
| 🧠 DeepSeek R1 Distill 8B | Q8 | 20 tok/s | 17 tok/s
+18%
| 9.5 GB | LM Studio | editorial | 2026-05-11 |
Phi-4 Medium | Q6 | 20 tok/s | 18 tok/s
+11%
| 11.4 GB | Jan | community | 2026-04-20 |
Qwen 2.5 VL 7B | Q8 | 20 tok/s | 17 tok/s
+18%
| 9.1 GB | Xybrid CLI | community | 2026-01-06 |
Gemma 3n E4B | FP16 | 19 tok/s | 20 tok/s
-5%
| 14.8 GB | Xybrid CLI | community | 2026-04-06 |
| 👁️ LLaVA 1.6 7B | FP16 | 19 tok/s | 19 tok/s
+0%
| 17.8 GB | Ollama | community | 2026-03-15 |
LFM2.5 8B A1B | Q8 | 19 tok/s | 16 tok/s
+19%
| 11.3 GB | LM Studio | editorial | 2026-03-02 |
LFM2.5 8B A1B | FP16 | 18 tok/s | 16 tok/s
+13%
| 19.6 GB | Ollama | community | 2026-01-16 |
Mistral 7B | FP16 | 18 tok/s | 19 tok/s
-5%
| 17.3 GB | Ollama | community | 2026-03-12 |
Phi-4 Medium | Q8 | 18 tok/s | 18 tok/s
+0%
| 16.4 GB | Ollama | community | 2026-02-06 |
| 👨💻 DeepSeek Coder 6.7B | FP16 | 18 tok/s | 20 tok/s
-10%
| 15.1 GB | Ollama | community | 2026-02-12 |
Qwen 2.5 Coder 7B | FP16 | 18 tok/s | 18 tok/s
+0%
| 17.2 GB | LM Studio | editorial | 2026-01-14 |
Llama 3.1 8B | FP16 | 17 tok/s | 17 tok/s
+0%
| 20.9 GB | Jan | community | 2026-04-21 |
| 🧠 DeepSeek R1 Distill 8B | FP16 | 17 tok/s | 17 tok/s
+0%
| 18.0 GB | Ollama | community | 2026-02-10 |
Qwen 3.5 9B | Q8 | 17 tok/s | 15 tok/s
+13%
| 10.2 GB | Jan | community | 2026-05-28 |
| 🧠 Qwen3 8B | Q8 | 17 tok/s | 16 tok/s
+6%
| 11.3 GB | Jan | community | 2026-02-22 |
Qwen 2.5 7B | FP16 | 16 tok/s | 18 tok/s
-11%
| 19.1 GB | Jan | community | 2026-02-22 |
Qwen 3.5 9B | FP16 | 16 tok/s | 15 tok/s
+7%
| 19.6 GB | Ollama | community | 2026-04-08 |
Qwen 2.5 VL 7B | FP16 | 16 tok/s | 17 tok/s
-6%
| 18.5 GB | Jan | community | 2026-04-09 |
Gemma 4 26B A4B | Q6 | 14 tok/s | 13 tok/s
+8%
| 23.5 GB | LM Studio | editorial | 2026-02-10 |
| 🧠 Qwen3 8B | FP16 | 14 tok/s | 16 tok/s
-12%
| 17.6 GB | LM Studio | community | 2026-04-21 |
Gemma 4 26B A4B | Q5 | 14 tok/s | 13 tok/s
+8%
| 21.3 GB | Xybrid CLI | community | 2026-05-13 |
| 👨💻 Laguna XS.2 | Q5 | 13 tok/s | 11 tok/s
+18%
| 25.7 GB | Jan | community | 2026-02-10 |
| 🎨 FLUX.1 Schnell | Q8 | 13 tok/s | 11 tok/s
+18%
| 13.9 GB | Ollama | community | 2026-02-26 |
Qwen 3.5 35B A3B | Q5 | 12 tok/s | 11 tok/s
+9%
| 26.9 GB | Jan | community | 2026-01-11 |
| 👨💻 Laguna XS.2 | Q6 | 12 tok/s | 11 tok/s
+9%
| 29.0 GB | LM Studio | editorial | 2026-05-11 |
| 🎨 FLUX.1 Schnell | FP16 | 12 tok/s | 11 tok/s
+9%
| 30.5 GB | Xybrid CLI | community | 2026-01-05 |
Gemma 3 12B | Q8 | 12 tok/s | 11 tok/s
+9%
| 15.5 GB | Xybrid CLI | community | 2026-01-21 |
Mistral Nemo 12B | Q8 | 12 tok/s | 11 tok/s
+9%
| 15.7 GB | Xybrid CLI | community | 2026-05-12 |
Qwen 3.5 35B A3B | Q4 | 12 tok/s | 11 tok/s
+9%
| 21.3 GB | Xybrid CLI | community | 2026-05-09 |
Gemma 3 12B | FP16 | 11 tok/s | 11 tok/s
+0%
| 29.0 GB | LM Studio | community | 2026-04-06 |
Gemma 4 31B | Q5 | 11 tok/s | 11 tok/s
+0%
| 25.5 GB | Xybrid CLI | community | 2026-05-23 |
Mistral Nemo 12B | FP16 | 10 tok/s | 11 tok/s
-9%
| 28.3 GB | Ollama | editorial | 2026-04-19 |
Gemma 4 31B | Q6 | 10 tok/s | 11 tok/s
-9%
| 27.7 GB | LM Studio | editorial | 2026-02-09 |