Qwen 2.5 Coder 1.5B | FP16 | 223 tok/s | 200 tok/s
+12%
| 3.8 GB | Xybrid CLI | community | 2026-04-18 |
| 🗣️ NeuTTS Air | FP16 | 223 tok/s | 200 tok/s
+12%
| 1.6 GB | Piper | community | 2026-03-12 |
| 🧠 DeepSeek R1 Distill 1.5B | FP16 | 222 tok/s | 200 tok/s
+11%
| 4.1 GB | Xybrid CLI | community | 2026-03-15 |
Qwen 3.5 2B | FP16 | 221 tok/s | 200 tok/s
+11%
| 5.2 GB | Ollama | community | 2026-01-14 |
| 🔢 GTE Large | FP16 | 221 tok/s | 200 tok/s
+11%
| 0.7 GB | LM Studio | community | 2026-02-11 |
Whisper Tiny | FP16 | 219 tok/s | 200 tok/s
+10%
| 0.1 GB | Whisper Transcription | community | 2026-04-19 |
| 🗣️ KittenTTS Nano | FP16 | 218 tok/s | 200 tok/s
+9%
| 0.1 GB | Piper | community | 2026-01-16 |
Llama 3.2 1B | FP16 | 217 tok/s | 200 tok/s
+9%
| 3.0 GB | Xybrid CLI | community | 2026-01-03 |
Gemma 4 E2B | FP16 | 215 tok/s | 200 tok/s
+8%
| 5.2 GB | Xybrid CLI | community | 2026-03-14 |
| 👁️ SmolVLM 500M | FP16 | 215 tok/s | 200 tok/s
+8%
| 1.4 GB | Ollama | editorial | 2026-04-08 |
| 🔢 Nomic Embed Text | FP16 | 215 tok/s | 200 tok/s
+8%
| 0.3 GB | Xybrid CLI | community | 2026-01-05 |
| 🎨 Stable Diffusion 3.5 Medium | FP16 | 215 tok/s | 200 tok/s
+8%
| 5.0 GB | Ollama | community | 2026-04-08 |
| 🗣️ Kokoro 82M | FP16 | 212 tok/s | 200 tok/s
+6%
| 0.4 GB | Xybrid CLI | community | 2026-03-15 |
Bonsai Image 4B | Q2 | 210 tok/s | 200 tok/s
+5%
| 2.1 GB | Jan | community | 2026-02-08 |
| 🔢 BGE Small | FP16 | 209 tok/s | 200 tok/s
+5%
| 0.1 GB | LM Studio | community | 2026-01-16 |
Qwen 2.5 0.5B | FP16 | 208 tok/s | 200 tok/s
+4%
| 1.3 GB | LM Studio | editorial | 2026-05-10 |
Ternary Bonsai 8B | Q2 | 207 tok/s | 200 tok/s
+4%
| 1.7 GB | LM Studio | community | 2026-03-03 |
Whisper Medium | FP16 | 205 tok/s | 200 tok/s
+3%
| 1.7 GB | Xybrid CLI | editorial | 2026-05-11 |
SmolLM2 360M | FP16 | 203 tok/s | 200 tok/s
+2%
| 1.2 GB | LM Studio | editorial | 2026-01-20 |
| 🔢 all-MiniLM-L6-v2 | FP16 | 203 tok/s | 200 tok/s
+2%
| 0.1 GB | Xybrid CLI | editorial | 2026-04-04 |
| 🗣️ KittenTTS Mini | FP16 | 202 tok/s | 200 tok/s
+1%
| 0.2 GB | Piper | community | 2026-04-06 |
| 👁️ Moondream 2B | FP16 | 201 tok/s | 200 tok/s
+1%
| 4.7 GB | Xybrid CLI | editorial | 2026-01-19 |
SmolLM2 135M | FP16 | 198 tok/s | 200 tok/s
-1%
| 0.3 GB | Ollama | editorial | 2026-04-01 |
| 🎨 Stable Diffusion Turbo | FP16 | 198 tok/s | 200 tok/s
-1%
| 2.3 GB | Xybrid CLI | editorial | 2026-04-06 |
| 🗣️ OuteTTS 0.3 500M | FP16 | 194 tok/s | 200 tok/s
-3%
| 1.1 GB | Piper | community | 2026-05-27 |
| 🎙️ Distil-Whisper Large V3 | FP16 | 194 tok/s | 200 tok/s
-3%
| 1.9 GB | Xybrid CLI | community | 2026-04-18 |
StableLM 2 1.6B | FP16 | 192 tok/s | 200 tok/s
-4%
| 3.9 GB | Ollama | community | 2026-04-20 |
Wav2Vec2 Base | FP16 | 192 tok/s | 200 tok/s
-4%
| 0.3 GB | Xybrid CLI | community | 2026-04-22 |
Gemma 3 1B | FP16 | 191 tok/s | 200 tok/s
-4%
| 2.7 GB | Ollama | community | 2026-04-19 |
| 🗣️ Dia 1.6B | FP16 | 191 tok/s | 200 tok/s
-4%
| 3.9 GB | Piper | community | 2026-04-19 |
TinyLlama 1.1B | FP16 | 186 tok/s | 200 tok/s
-7%
| 2.6 GB | LM Studio | community | 2026-02-10 |
Ternary Bonsai 1.7B | Q2 | 186 tok/s | 200 tok/s
-7%
| 0.5 GB | LM Studio | editorial | 2026-05-25 |
Ternary Bonsai 4B | Q2 | 185 tok/s | 200 tok/s
-7%
| 1.1 GB | LM Studio | editorial | 2026-05-24 |
Qwen 3.5 0.8B | FP16 | 185 tok/s | 200 tok/s
-7%
| 2.1 GB | LM Studio | editorial | 2026-02-09 |
Whisper Small | FP16 | 184 tok/s | 200 tok/s
-8%
| 0.6 GB | Xybrid CLI | editorial | 2026-02-12 |
LFM2.5 1.2B | FP16 | 181 tok/s | 200 tok/s
-9%
| 2.5 GB | Xybrid CLI | community | 2026-02-01 |
SmolLM2 1.7B | FP16 | 180 tok/s | 200 tok/s
-10%
| 4.2 GB | Xybrid CLI | community | 2026-05-24 |
Bonsai 8B (1-bit) | Q1 | 180 tok/s | 200 tok/s
-10%
| 1.5 GB | Xybrid CLI | editorial | 2026-04-18 |
Qwen 2.5 Coder 0.5B | FP16 | 177 tok/s | 200 tok/s
-11%
| 1.4 GB | LM Studio | editorial | 2026-03-13 |
Whisper Large V3 | FP16 | 177 tok/s | 200 tok/s
-11%
| 3.8 GB | Whisper Transcription | community | 2026-02-19 |
Qwen 2.5 Coder 3B | FP16 | 167 tok/s | 150 tok/s
+11%
| 7.7 GB | Jan | community | 2026-01-18 |
| 👨💻 StarCoder2 3B | FP16 | 164 tok/s | 155 tok/s
+6%
| 7.3 GB | Jan | community | 2026-04-17 |
Qwen 2.5 3B | FP16 | 152 tok/s | 150 tok/s
+1%
| 7.3 GB | LM Studio | editorial | 2026-01-13 |
| 🎨 SDXL Turbo | FP16 | 152 tok/s | 148 tok/s
+3%
| 7.5 GB | LM Studio | editorial | 2026-04-06 |
Llama 3.2 3B | FP16 | 134 tok/s | 145 tok/s
-8%
| 8.5 GB | Jan | community | 2026-02-21 |
Qwen 3.5 4B | FP16 | 130 tok/s | 117 tok/s
+11%
| 10.2 GB | Jan | community | 2026-02-24 |
Phi-4 Mini | FP16 | 125 tok/s | 123 tok/s
+2%
| 8.9 GB | Ollama | community | 2026-01-04 |
Mistral 7B | Q8 | 125 tok/s | 117 tok/s
+7%
| 9.8 GB | LM Studio | community | 2026-05-09 |
| 🧠 DeepSeek R1 Distill 7B | Q8 | 121 tok/s | 119 tok/s
+2%
| 8.9 GB | LM Studio | community | 2026-05-10 |
Qwen 2.5 Coder 7B | Q8 | 121 tok/s | 119 tok/s
+2%
| 10.4 GB | Jan | community | 2026-01-01 |
Gemma 3 4B | FP16 | 118 tok/s | 108 tok/s
+9%
| 9.6 GB | Ollama | community | 2026-04-07 |
| 🧠 Qwen3 8B | Q8 | 118 tok/s | 110 tok/s
+7%
| 9.5 GB | Ollama | community | 2026-03-02 |
Gemma 3n E2B | FP16 | 114 tok/s | 108 tok/s
+6%
| 11.4 GB | Jan | community | 2026-05-24 |
Qwen 2.5 VL 7B | Q8 | 114 tok/s | 113 tok/s
+1%
| 9.6 GB | Ollama | community | 2026-01-03 |
Qwen 2.5 7B | Q8 | 113 tok/s | 119 tok/s
-5%
| 9.8 GB | Ollama | community | 2026-03-15 |
Llama 3.1 8B | Q8 | 113 tok/s | 113 tok/s
+0%
| 9.5 GB | LM Studio | editorial | 2026-04-02 |
LFM2.5 8B A1B | Q8 | 113 tok/s | 109 tok/s
+4%
| 9.3 GB | Xybrid CLI | community | 2026-05-26 |
| 🧠 DeepSeek R1 Distill 8B | Q8 | 111 tok/s | 113 tok/s
-2%
| 10.6 GB | Xybrid CLI | editorial | 2026-02-25 |
Gemma 4 E4B | FP16 | 108 tok/s | 107 tok/s
+1%
| 10.2 GB | Ollama | community | 2026-02-09 |
Qwen 3.5 9B | Q8 | 97 tok/s | 99 tok/s
-2%
| 10.6 GB | Ollama | community | 2026-02-08 |
Phi-4 Medium | Q6 | 89 tok/s | 89 tok/s
+0%
| 13.3 GB | Xybrid CLI | community | 2026-02-24 |
Qwen 3.5 35B A3B | Q2 | 85 tok/s | 80 tok/s
+6%
| 15.5 GB | LM Studio | editorial | 2026-02-26 |
Gemma 3 12B | Q8 | 78 tok/s | 74 tok/s
+5%
| 13.9 GB | Xybrid CLI | community | 2026-05-27 |
Mistral Nemo 12B | Q8 | 71 tok/s | 74 tok/s
-4%
| 14.0 GB | Xybrid CLI | community | 2026-04-06 |
| 👨💻 DeepSeek Coder 6.7B | FP16 | 70 tok/s | 70 tok/s
+0%
| 14.8 GB | LM Studio | community | 2026-04-05 |
Gemma 4 26B A4B | Q3 | 69 tok/s | 77 tok/s
-10%
| 15.3 GB | Jan | community | 2026-03-26 |
| 🎨 FLUX.1 Schnell | Q8 | 67 tok/s | 76 tok/s
-12%
| 16.0 GB | Jan | community | 2026-03-26 |
Gemma 3n E4B | FP16 | 64 tok/s | 70 tok/s
-9%
| 15.5 GB | LM Studio | editorial | 2026-03-16 |
Gemma 4 31B | Q3 | 63 tok/s | 71 tok/s
-11%
| 16.9 GB | Jan | community | 2026-02-19 |
| 👨💻 Laguna XS.2 | Q3 | 62 tok/s | 69 tok/s
-10%
| 15.7 GB | Xybrid CLI | editorial | 2026-05-25 |
| 👁️ LLaVA 1.6 7B | FP16 | 62 tok/s | 67 tok/s
-7%
| 17.9 GB | Jan | community | 2026-02-21 |