Gaming PC (RTX 3070) 32GB

Windows High tier · Intel Core i5 / AMD Ryzen 5 · 32 GB RAM · 448 GB/s bandwidth
View device page →
BENCHMARK RESULTS (71)
Model Quant Measured Estimated RAM used App Source Date
🗣️ NeuTTS Air FP16 223 tok/s 200 tok/s +12% 1.6 GB Piper community 2026-03-04
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 221 tok/s 200 tok/s +11% 0.4 GB LM Studio editorial 2026-02-11
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 220 tok/s 200 tok/s +10% 1.3 GB Ollama community 2026-03-02
Whisper Medium Whisper Medium FP16 220 tok/s 200 tok/s +10% 1.8 GB Whisper Transcription community 2026-04-22
Wav2Vec2 Base Wav2Vec2 Base FP16 219 tok/s 200 tok/s +10% 0.2 GB Xybrid CLI community 2026-03-01
Ternary Bonsai 4B Ternary Bonsai 4B Q2 217 tok/s 200 tok/s +9% 1.0 GB Ollama community 2026-01-15
SmolLM2 360M SmolLM2 360M FP16 216 tok/s 200 tok/s +8% 1.0 GB Xybrid CLI community 2026-01-02
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 214 tok/s 200 tok/s +7% 1.2 GB Xybrid CLI community 2026-01-05
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 213 tok/s 200 tok/s +7% 1.4 GB Jan community 2026-03-24
🗣️ Kokoro 82M FP16 213 tok/s 200 tok/s +7% 0.4 GB Piper community 2026-01-18
Whisper Tiny Whisper Tiny FP16 209 tok/s 200 tok/s +5% 0.1 GB Whisper Transcription community 2026-01-04
👁️ SmolVLM 500M FP16 208 tok/s 200 tok/s +4% 1.2 GB Jan community 2026-04-23
🎨 Stable Diffusion Turbo FP16 208 tok/s 200 tok/s +4% 2.7 GB LM Studio editorial 2026-02-26
🔢 GTE Large FP16 207 tok/s 200 tok/s +4% 0.7 GB Jan community 2026-02-09
SmolLM2 135M SmolLM2 135M FP16 206 tok/s 200 tok/s +3% 0.3 GB LM Studio editorial 2026-05-08
🔢 Nomic Embed Text FP16 206 tok/s 200 tok/s +3% 0.3 GB Jan community 2026-03-14
🔢 all-MiniLM-L6-v2 FP16 205 tok/s 200 tok/s +3% 0.1 GB LM Studio editorial 2026-02-24
🗣️ OuteTTS 0.3 500M FP16 202 tok/s 200 tok/s +1% 1.1 GB Xybrid CLI editorial 2026-04-03
🎙️ Distil-Whisper Large V3 FP16 195 tok/s 200 tok/s -2% 1.6 GB Xybrid CLI community 2026-01-02
🗣️ KittenTTS Nano FP16 191 tok/s 200 tok/s -4% 0.1 GB Xybrid CLI community 2026-02-22
Whisper Small Whisper Small FP16 191 tok/s 200 tok/s -4% 0.6 GB Whisper Transcription community 2026-02-22
🗣️ KittenTTS Mini FP16 189 tok/s 200 tok/s -5% 0.2 GB Piper community 2026-05-24
LFM2.5 1.2B LFM2.5 1.2B FP16 184 tok/s 191 tok/s -4% 2.5 GB LM Studio community 2026-01-04
Gemma 3 1B Gemma 3 1B FP16 182 tok/s 200 tok/s -9% 2.5 GB Jan community 2026-05-14
Ternary Bonsai 8B Ternary Bonsai 8B Q2 182 tok/s 200 tok/s -9% 2.0 GB Jan community 2026-03-28
🔢 BGE Small FP16 182 tok/s 200 tok/s -9% 0.1 GB Jan community 2026-05-11
Bonsai Image 4B Bonsai Image 4B Q2 182 tok/s 200 tok/s -9% 2.1 GB LM Studio community 2026-03-14
TinyLlama 1.1B TinyLlama 1.1B FP16 178 tok/s 200 tok/s -11% 2.8 GB LM Studio editorial 2026-05-26
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 177 tok/s 200 tok/s -11% 2.0 GB Ollama community 2026-04-11
Llama 3.2 1B Llama 3.2 1B FP16 150 tok/s 166 tok/s -10% 3.4 GB Xybrid CLI editorial 2026-05-24
🗣️ Dia 1.6B FP16 146 tok/s 136 tok/s +7% 4.2 GB Piper editorial 2026-03-02
Whisper Large V3 Whisper Large V3 FP16 140 tok/s 145 tok/s -3% 3.4 GB Xybrid CLI community 2026-05-26
🧠 DeepSeek R1 Distill 1.5B FP16 139 tok/s 136 tok/s +2% 4.1 GB Jan community 2026-01-01
SmolLM2 1.7B SmolLM2 1.7B FP16 130 tok/s 132 tok/s -2% 3.9 GB Xybrid CLI editorial 2026-04-03
StableLM 2 1.6B StableLM 2 1.6B FP16 127 tok/s 136 tok/s -7% 4.0 GB Xybrid CLI community 2026-01-19
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 124 tok/s 140 tok/s -11% 4.0 GB Jan community 2026-02-20
👁️ Moondream 2B FP16 121 tok/s 121 tok/s +0% 4.1 GB LM Studio editorial 2026-05-11
Qwen 3.5 2B Qwen 3.5 2B FP16 112 tok/s 107 tok/s +5% 4.9 GB Jan community 2026-02-07
Qwen 3.5 4B Qwen 3.5 4B Q8 111 tok/s 102 tok/s +9% 5.2 GB Xybrid CLI community 2026-04-21
Phi-4 Mini Phi-4 Mini Q8 111 tok/s 102 tok/s +9% 4.9 GB Xybrid CLI editorial 2026-05-28
Gemma 3 4B Gemma 3 4B Q8 100 tok/s 91 tok/s +10% 5.5 GB Xybrid CLI editorial 2026-02-07
Gemma 3n E2B Gemma 3n E2B Q8 98 tok/s 94 tok/s +4% 5.6 GB Jan community 2026-03-12
Gemma 4 E2B Gemma 4 E2B FP16 97 tok/s 100 tok/s -3% 5.4 GB Ollama community 2026-03-15
🎨 Stable Diffusion 3.5 Medium FP16 92 tok/s 97 tok/s -5% 5.6 GB Ollama community 2026-04-21
👁️ LLaVA 1.6 7B Q6 86 tok/s 81 tok/s +6% 6.3 GB Jan community 2026-02-09
Gemma 4 E4B Gemma 4 E4B Q8 81 tok/s 90 tok/s -10% 5.6 GB LM Studio editorial 2026-03-15
👨‍💻 StarCoder2 3B FP16 81 tok/s 72 tok/s +13% 6.8 GB LM Studio community 2026-03-13
Llama 3.1 8B Llama 3.1 8B Q6 80 tok/s 72 tok/s +11% 7.9 GB Ollama editorial 2026-05-05
Qwen 2.5 7B Qwen 2.5 7B Q6 79 tok/s 76 tok/s +4% 6.3 GB LM Studio community 2026-03-04
Mistral 7B Mistral 7B Q6 78 tok/s 76 tok/s +3% 6.5 GB Jan community 2026-02-08
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 78 tok/s 70 tok/s +11% 8.0 GB Ollama editorial 2026-02-06
Llama 3.2 3B Llama 3.2 3B FP16 75 tok/s 68 tok/s +10% 7.9 GB Xybrid CLI community 2026-05-23
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q6 75 tok/s 76 tok/s -1% 6.6 GB Xybrid CLI community 2026-01-13
Qwen 2.5 3B Qwen 2.5 3B FP16 73 tok/s 70 tok/s +4% 6.8 GB LM Studio community 2026-02-26
Gemma 3n E4B Gemma 3n E4B Q6 73 tok/s 71 tok/s +3% 6.9 GB Jan community 2026-02-07
🧠 DeepSeek R1 Distill 7B Q6 72 tok/s 76 tok/s -5% 6.3 GB Ollama community 2026-01-05
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q6 72 tok/s 72 tok/s +0% 6.7 GB LM Studio community 2026-05-10
🧠 DeepSeek R1 Distill 8B Q6 71 tok/s 72 tok/s -1% 8.0 GB Ollama community 2026-04-23
🎨 SDXL Turbo FP16 71 tok/s 69 tok/s +3% 6.9 GB LM Studio community 2026-03-03
Mistral Nemo 12B Mistral Nemo 12B Q4 69 tok/s 65 tok/s +6% 7.6 GB Jan community 2026-05-08
👨‍💻 DeepSeek Coder 6.7B Q8 69 tok/s 62 tok/s +11% 8.2 GB Jan community 2026-05-12
🎨 FLUX.1 Schnell Q4 69 tok/s 66 tok/s +5% 8.6 GB LM Studio editorial 2026-03-04
Gemma 3 12B Gemma 3 12B Q4 68 tok/s 64 tok/s +6% 7.5 GB LM Studio community 2026-03-03
Phi-4 Medium Phi-4 Medium Q3 67 tok/s 75 tok/s -11% 6.7 GB LM Studio editorial 2026-01-06
LFM2.5 8B A1B LFM2.5 8B A1B Q6 65 tok/s 70 tok/s -7% 7.6 GB Jan community 2026-05-16
Qwen 3.5 9B Qwen 3.5 9B Q6 64 tok/s 64 tok/s +0% 7.5 GB LM Studio community 2026-05-10
🧠 Qwen3 8B Q6 64 tok/s 71 tok/s -10% 6.9 GB LM Studio community 2026-02-07
👨‍💻 Laguna XS.2 Q3 34 tok/s 32 tok/s +6% 17.9 GB Ollama editorial 2026-02-27
Gemma 4 31B Gemma 4 31B Q3 31 tok/s 33 tok/s -6% 16.2 GB Jan community 2026-01-17
Gemma 4 26B A4B Gemma 4 26B A4B Q4 30 tok/s 28 tok/s +7% 18.4 GB Ollama community 2026-04-06
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q3 28 tok/s 30 tok/s -7% 17.6 GB Ollama community 2026-03-15
← All benchmarks