| 🗣️ KittenTTS Nano | FP16 | 224 tok/s | 200 tok/s
+12%
| 0.1 GB | Piper | community | 2026-03-04 |
SmolLM2 135M | FP16 | 223 tok/s | 200 tok/s
+12%
| 0.3 GB | Ollama | community | 2026-02-21 |
Whisper Small | FP16 | 219 tok/s | 200 tok/s
+10%
| 0.5 GB | MacWhisper | community | 2026-04-07 |
| 🗣️ NeuTTS Air | FP16 | 217 tok/s | 200 tok/s
+9%
| 1.8 GB | Xybrid CLI | community | 2026-04-21 |
TinyLlama 1.1B | FP16 | 216 tok/s | 200 tok/s
+8%
| 2.6 GB | Jan | community | 2026-04-17 |
Bonsai Image 4B | Q2 | 216 tok/s | 200 tok/s
+8%
| 2.0 GB | Xybrid CLI | community | 2026-01-02 |
| 🗣️ Kokoro 82M | FP16 | 216 tok/s | 200 tok/s
+8%
| 0.4 GB | Xybrid CLI | community | 2026-01-05 |
Qwen 2.5 0.5B | FP16 | 214 tok/s | 200 tok/s
+7%
| 1.4 GB | Xybrid CLI | community | 2026-03-13 |
Bonsai 8B (1-bit) | Q1 | 213 tok/s | 200 tok/s
+7%
| 1.5 GB | Xybrid CLI | community | 2026-02-07 |
| 🔢 all-MiniLM-L6-v2 | FP16 | 211 tok/s | 200 tok/s
+6%
| 0.1 GB | LM Studio | community | 2026-03-02 |
| 🔢 BGE Small | FP16 | 210 tok/s | 200 tok/s
+5%
| 0.1 GB | LM Studio | community | 2026-03-02 |
Whisper Medium | FP16 | 208 tok/s | 200 tok/s
+4%
| 1.8 GB | Xybrid CLI | community | 2026-03-13 |
| 🔢 Nomic Embed Text | FP16 | 204 tok/s | 200 tok/s
+2%
| 0.3 GB | Ollama | community | 2026-01-04 |
Llama 3.2 1B | FP16 | 201 tok/s | 200 tok/s
+1%
| 3.4 GB | LM Studio | editorial | 2026-02-22 |
Whisper Tiny | FP16 | 201 tok/s | 200 tok/s
+1%
| 0.1 GB | Xybrid CLI | editorial | 2026-04-02 |
LFM2.5 1.2B | FP16 | 200 tok/s | 200 tok/s
+0%
| 2.6 GB | Ollama | community | 2026-01-05 |
| 🎙️ Distil-Whisper Large V3 | FP16 | 195 tok/s | 200 tok/s
-2%
| 1.6 GB | MacWhisper | community | 2026-05-27 |
Qwen 3.5 0.8B | FP16 | 194 tok/s | 200 tok/s
-3%
| 1.9 GB | Ollama | community | 2026-02-07 |
| 🎨 Stable Diffusion Turbo | FP16 | 194 tok/s | 200 tok/s
-3%
| 2.2 GB | Ollama | community | 2026-01-04 |
Ternary Bonsai 1.7B | Q2 | 192 tok/s | 200 tok/s
-4%
| 0.5 GB | Ollama | community | 2026-04-20 |
| 👁️ SmolVLM 500M | FP16 | 191 tok/s | 200 tok/s
-4%
| 1.4 GB | Xybrid CLI | community | 2026-04-05 |
| 🗣️ OuteTTS 0.3 500M | FP16 | 190 tok/s | 200 tok/s
-5%
| 1.3 GB | Xybrid CLI | community | 2026-03-27 |
SmolLM2 360M | FP16 | 187 tok/s | 200 tok/s
-6%
| 1.1 GB | Jan | community | 2026-02-23 |
Gemma 3 1B | FP16 | 184 tok/s | 200 tok/s
-8%
| 2.7 GB | Jan | community | 2026-02-18 |
Wav2Vec2 Base | FP16 | 184 tok/s | 200 tok/s
-8%
| 0.3 GB | MacWhisper | editorial | 2026-05-24 |
Qwen 2.5 Coder 0.5B | FP16 | 183 tok/s | 200 tok/s
-8%
| 1.4 GB | Jan | community | 2026-05-12 |
| 🗣️ KittenTTS Mini | FP16 | 181 tok/s | 200 tok/s
-9%
| 0.2 GB | Xybrid CLI | community | 2026-04-10 |
| 🔢 GTE Large | FP16 | 180 tok/s | 200 tok/s
-10%
| 0.8 GB | Jan | community | 2026-05-12 |
Ternary Bonsai 4B | Q2 | 179 tok/s | 200 tok/s
-10%
| 1.0 GB | Ollama | community | 2026-01-17 |
Qwen 2.5 Coder 1.5B | FP16 | 179 tok/s | 171 tok/s
+5%
| 3.4 GB | Jan | community | 2026-05-24 |
Ternary Bonsai 8B | Q2 | 177 tok/s | 200 tok/s
-11%
| 1.9 GB | Ollama | community | 2026-02-22 |
Whisper Large V3 | FP16 | 175 tok/s | 176 tok/s
-1%
| 3.5 GB | MacWhisper | community | 2026-02-10 |
| 🧠 DeepSeek R1 Distill 1.5B | FP16 | 171 tok/s | 165 tok/s
+4%
| 3.8 GB | LM Studio | editorial | 2026-05-12 |
SmolLM2 1.7B | FP16 | 170 tok/s | 161 tok/s
+6%
| 4.4 GB | Xybrid CLI | community | 2026-01-03 |
StableLM 2 1.6B | FP16 | 168 tok/s | 165 tok/s
+2%
| 3.8 GB | Ollama | community | 2026-01-04 |
| 🗣️ Dia 1.6B | FP16 | 168 tok/s | 165 tok/s
+2%
| 4.3 GB | Piper | editorial | 2026-01-21 |
| 👁️ Moondream 2B | FP16 | 157 tok/s | 148 tok/s
+6%
| 4.6 GB | Xybrid CLI | community | 2026-05-26 |
Gemma 4 E2B | FP16 | 132 tok/s | 121 tok/s
+9%
| 4.8 GB | LM Studio | community | 2026-02-10 |
Qwen 3.5 2B | FP16 | 122 tok/s | 130 tok/s
-6%
| 5.0 GB | Xybrid CLI | community | 2026-05-14 |
| 🎨 Stable Diffusion 3.5 Medium | FP16 | 119 tok/s | 119 tok/s
+0%
| 5.2 GB | Xybrid CLI | editorial | 2026-05-08 |
Qwen 2.5 Coder 3B | FP16 | 95 tok/s | 85 tok/s
+12%
| 7.7 GB | Xybrid CLI | community | 2026-04-21 |
Llama 3.2 3B | FP16 | 86 tok/s | 83 tok/s
+4%
| 8.4 GB | LM Studio | editorial | 2026-02-23 |
| 👨💻 StarCoder2 3B | FP16 | 84 tok/s | 88 tok/s
-5%
| 6.7 GB | Xybrid CLI | community | 2026-04-03 |
Phi-4 Mini | FP16 | 78 tok/s | 70 tok/s
+11%
| 9.4 GB | Jan | community | 2026-02-19 |
Qwen 2.5 3B | FP16 | 76 tok/s | 85 tok/s
-11%
| 7.2 GB | Jan | community | 2026-05-12 |
| 🎨 SDXL Turbo | FP16 | 76 tok/s | 84 tok/s
-10%
| 8.0 GB | Xybrid CLI | community | 2026-04-18 |
Gemma 4 E4B | FP16 | 66 tok/s | 61 tok/s
+8%
| 9.6 GB | Xybrid CLI | community | 2026-05-28 |
Gemma 3 4B | FP16 | 62 tok/s | 61 tok/s
+2%
| 10.1 GB | LM Studio | editorial | 2026-05-12 |
Qwen 3.5 4B | FP16 | 61 tok/s | 67 tok/s
-9%
| 9.3 GB | Jan | community | 2026-05-13 |
Gemma 3n E2B | FP16 | 56 tok/s | 61 tok/s
-8%
| 11.5 GB | LM Studio | editorial | 2026-01-01 |
Gemma 3n E4B | FP16 | 44 tok/s | 40 tok/s
+10%
| 16.3 GB | Xybrid CLI | community | 2026-03-14 |
| 🧠 DeepSeek R1 Distill 7B | FP16 | 39 tok/s | 35 tok/s
+11%
| 18.5 GB | Xybrid CLI | community | 2026-04-20 |
| 👨💻 DeepSeek Coder 6.7B | FP16 | 37 tok/s | 40 tok/s
-7%
| 16.7 GB | LM Studio | community | 2026-03-22 |
Llama 3.1 8B | FP16 | 36 tok/s | 34 tok/s
+6%
| 17.2 GB | LM Studio | community | 2026-02-24 |
Mistral 7B | FP16 | 36 tok/s | 37 tok/s
-3%
| 16.0 GB | Ollama | community | 2026-01-04 |
Qwen 2.5 7B | FP16 | 35 tok/s | 35 tok/s
+0%
| 19.2 GB | LM Studio | community | 2026-01-20 |
| 👁️ LLaVA 1.6 7B | FP16 | 35 tok/s | 38 tok/s
-8%
| 18.1 GB | LM Studio | editorial | 2026-01-03 |
Qwen 2.5 VL 7B | FP16 | 35 tok/s | 34 tok/s
+3%
| 20.8 GB | Jan | community | 2026-04-20 |
| 🧠 DeepSeek R1 Distill 8B | FP16 | 34 tok/s | 34 tok/s
+0%
| 18.0 GB | LM Studio | editorial | 2026-05-10 |
LFM2.5 8B A1B | FP16 | 33 tok/s | 33 tok/s
+0%
| 18.0 GB | Ollama | community | 2026-02-11 |
Qwen 2.5 Coder 7B | FP16 | 32 tok/s | 35 tok/s
-9%
| 19.1 GB | Xybrid CLI | community | 2026-04-19 |
| 🧠 Qwen3 8B | FP16 | 30 tok/s | 33 tok/s
-9%
| 21.5 GB | Jan | community | 2026-02-23 |
Qwen 3.5 9B | FP16 | 28 tok/s | 30 tok/s
-7%
| 23.6 GB | Jan | community | 2026-04-02 |
| 🎨 FLUX.1 Schnell | FP16 | 24 tok/s | 23 tok/s
+4%
| 30.4 GB | LM Studio | editorial | 2026-03-02 |
Mistral Nemo 12B | FP16 | 23 tok/s | 22 tok/s
+5%
| 28.0 GB | Jan | community | 2026-03-12 |
| 👨💻 Laguna XS.2 | Q6 | 23 tok/s | 22 tok/s
+5%
| 28.0 GB | Jan | community | 2026-03-12 |
Qwen 3.5 35B A3B | Q6 | 22 tok/s | 20 tok/s
+10%
| 28.7 GB | Xybrid CLI | community | 2026-05-28 |
Gemma 3 12B | FP16 | 21 tok/s | 22 tok/s
-5%
| 26.5 GB | Jan | community | 2026-01-14 |
Phi-4 Medium | FP16 | 21 tok/s | 20 tok/s
+5%
| 29.5 GB | Xybrid CLI | community | 2026-02-08 |
Gemma 4 26B A4B | Q8 | 19 tok/s | 20 tok/s
-5%
| 33.6 GB | Xybrid CLI | community | 2026-05-13 |
Qwen3 Coder Next | Q2 | 18 tok/s | 20 tok/s
-10%
| 31.4 GB | Jan | community | 2026-05-12 |
Gemma 4 31B | Q8 | 15 tok/s | 17 tok/s
-12%
| 40.8 GB | LM Studio | community | 2026-04-22 |