Gaming PC (RTX 4090) 64GB

Windows Ultra tier · Intel Core i9 / AMD Ryzen 9 · 64 GB RAM · 1008 GB/s bandwidth
View device page →
BENCHMARK RESULTS (75)
Model Quant Measured Estimated RAM used App Source Date
Llama 3.2 1B Llama 3.2 1B FP16 224 tok/s 200 tok/s +12% 3.4 GB Jan community 2026-02-19
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 222 tok/s 200 tok/s +11% 1.5 GB Ollama community 2026-02-23
Whisper Medium Whisper Medium FP16 222 tok/s 200 tok/s +11% 1.7 GB Whisper Transcription editorial 2026-02-09
Ternary Bonsai 8B Ternary Bonsai 8B Q2 220 tok/s 200 tok/s +10% 1.9 GB Xybrid CLI community 2026-05-23
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 219 tok/s 200 tok/s +10% 3.6 GB Ollama community 2026-03-04
🔢 Nomic Embed Text FP16 219 tok/s 200 tok/s +10% 0.3 GB Ollama community 2026-02-19
🗣️ KittenTTS Nano FP16 218 tok/s 200 tok/s +9% 0.1 GB Xybrid CLI community 2026-01-04
SmolLM2 135M SmolLM2 135M FP16 216 tok/s 200 tok/s +8% 0.3 GB Ollama community 2026-03-28
Whisper Large V3 Whisper Large V3 FP16 216 tok/s 200 tok/s +8% 3.3 GB Whisper Transcription community 2026-01-02
TinyLlama 1.1B TinyLlama 1.1B FP16 214 tok/s 200 tok/s +7% 2.6 GB LM Studio community 2026-05-10
Gemma 4 E2B Gemma 4 E2B FP16 214 tok/s 200 tok/s +7% 5.8 GB Ollama community 2026-03-01
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 213 tok/s 200 tok/s +7% 2.1 GB LM Studio community 2026-05-09
🎨 Stable Diffusion Turbo FP16 211 tok/s 200 tok/s +6% 2.7 GB Jan community 2026-01-02
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 210 tok/s 200 tok/s +5% 1.3 GB Xybrid CLI community 2026-05-27
Ternary Bonsai 4B Ternary Bonsai 4B Q2 208 tok/s 200 tok/s +4% 0.9 GB LM Studio community 2026-02-26
Gemma 3 1B Gemma 3 1B FP16 205 tok/s 200 tok/s +3% 2.5 GB LM Studio editorial 2026-05-11
🧠 DeepSeek R1 Distill 1.5B FP16 203 tok/s 200 tok/s +2% 4.1 GB LM Studio community 2026-01-20
👁️ SmolVLM 500M FP16 203 tok/s 200 tok/s +2% 1.2 GB Jan community 2026-03-12
Bonsai Image 4B Bonsai Image 4B Q2 201 tok/s 200 tok/s +1% 2.2 GB Xybrid CLI community 2026-01-19
Mistral 7B Mistral 7B Q4 200 tok/s 69 tok/s +190% 4.3 GB LM Studio editorial 2026-03-20
Phi-4 Mini Phi-4 Mini Q8 200 tok/s 129 tok/s +55% 4.6 GB Ollama editorial 2026-03-20
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 196 tok/s 200 tok/s -2% 1.4 GB Xybrid CLI community 2026-05-16
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 196 tok/s 200 tok/s -2% 0.5 GB Xybrid CLI community 2026-01-19
🗣️ OuteTTS 0.3 500M FP16 194 tok/s 200 tok/s -3% 1.2 GB Xybrid CLI community 2026-05-15
🔢 all-MiniLM-L6-v2 FP16 193 tok/s 200 tok/s -4% 0.1 GB Ollama community 2026-03-14
🗣️ Dia 1.6B FP16 193 tok/s 200 tok/s -4% 3.6 GB Xybrid CLI community 2026-04-04
🎙️ Distil-Whisper Large V3 FP16 193 tok/s 200 tok/s -4% 1.6 GB Whisper Transcription community 2026-03-01
🗣️ NeuTTS Air FP16 191 tok/s 200 tok/s -4% 1.6 GB Xybrid CLI community 2026-04-06
LFM2.5 1.2B LFM2.5 1.2B FP16 189 tok/s 200 tok/s -5% 2.5 GB Xybrid CLI community 2026-03-27
🗣️ KittenTTS Mini FP16 188 tok/s 200 tok/s -6% 0.2 GB Piper community 2026-03-14
StableLM 2 1.6B StableLM 2 1.6B FP16 187 tok/s 200 tok/s -6% 3.5 GB Jan community 2026-03-28
🎨 Stable Diffusion 3.5 Medium FP16 186 tok/s 200 tok/s -7% 5.8 GB LM Studio editorial 2026-01-02
🔢 GTE Large FP16 184 tok/s 200 tok/s -8% 0.9 GB Jan community 2026-03-01
🗣️ Kokoro 82M FP16 184 tok/s 200 tok/s -8% 0.4 GB Xybrid CLI community 2026-05-15
SmolLM2 360M SmolLM2 360M FP16 183 tok/s 200 tok/s -8% 1.1 GB LM Studio editorial 2026-04-20
Whisper Tiny Whisper Tiny FP16 183 tok/s 200 tok/s -8% 0.1 GB Whisper Transcription community 2026-05-14
SmolLM2 1.7B SmolLM2 1.7B FP16 182 tok/s 200 tok/s -9% 3.9 GB Jan community 2026-05-13
🔢 BGE Small FP16 182 tok/s 200 tok/s -9% 0.1 GB LM Studio community 2026-03-16
Qwen 3.5 2B Qwen 3.5 2B FP16 181 tok/s 200 tok/s -9% 4.9 GB LM Studio community 2026-02-07
👁️ Moondream 2B FP16 177 tok/s 200 tok/s -11% 4.6 GB Xybrid CLI editorial 2026-03-17
Wav2Vec2 Base Wav2Vec2 Base FP16 177 tok/s 200 tok/s -11% 0.3 GB Whisper Transcription community 2026-03-25
Whisper Small Whisper Small FP16 177 tok/s 200 tok/s -11% 0.6 GB Whisper Transcription community 2026-02-19
Qwen 2.5 3B Qwen 2.5 3B FP16 172 tok/s 158 tok/s +9% 7.1 GB Xybrid CLI editorial 2026-02-10
👨‍💻 StarCoder2 3B FP16 163 tok/s 163 tok/s +0% 7.9 GB LM Studio editorial 2026-02-27
🎨 SDXL Turbo FP16 160 tok/s 155 tok/s +3% 8.2 GB Jan community 2026-04-22
Llama 3.2 3B Llama 3.2 3B FP16 152 tok/s 153 tok/s -1% 8.1 GB Ollama community 2026-03-18
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 151 tok/s 158 tok/s -4% 7.5 GB Ollama community 2026-03-16
Phi-4 Mini Phi-4 Mini FP16 121 tok/s 129 tok/s -6% 9.1 GB Jan community 2026-05-11
Gemma 3 4B Gemma 3 4B FP16 113 tok/s 113 tok/s +0% 9.6 GB Ollama community 2026-02-08
Gemma 4 E4B Gemma 4 E4B FP16 109 tok/s 112 tok/s -3% 11.2 GB Xybrid CLI community 2026-01-21
Gemma 3n E2B Gemma 3n E2B FP16 108 tok/s 113 tok/s -4% 9.6 GB Xybrid CLI community 2026-03-25
Qwen 3.5 4B Qwen 3.5 4B FP16 108 tok/s 123 tok/s -12% 8.7 GB Xybrid CLI community 2026-03-13
Gemma 3n E4B Gemma 3n E4B FP16 75 tok/s 74 tok/s +1% 15.7 GB LM Studio editorial 2026-01-13
👁️ LLaVA 1.6 7B FP16 75 tok/s 70 tok/s +7% 15.5 GB Xybrid CLI community 2026-05-26
Gemma 3 12B Gemma 3 12B Q8 72 tok/s 78 tok/s -8% 16.3 GB Jan community 2026-03-24
🎨 FLUX.1 Schnell Q8 72 tok/s 79 tok/s -9% 14.5 GB Ollama editorial 2026-03-17
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 71 tok/s 65 tok/s +9% 18.3 GB Ollama community 2026-02-22
Mistral Nemo 12B Mistral Nemo 12B Q8 70 tok/s 78 tok/s -10% 14.5 GB LM Studio editorial 2026-03-15
👨‍💻 DeepSeek Coder 6.7B FP16 70 tok/s 74 tok/s -5% 15.5 GB Ollama editorial 2026-03-06
Mistral 7B Mistral 7B FP16 69 tok/s 69 tok/s +0% 18.1 GB Jan community 2026-04-19
Llama 3.1 8B Llama 3.1 8B FP16 68 tok/s 63 tok/s +8% 20.5 GB Xybrid CLI community 2026-05-28
🧠 DeepSeek R1 Distill 8B FP16 67 tok/s 63 tok/s +6% 19.1 GB Jan community 2026-04-18
Phi-4 Medium Phi-4 Medium Q8 65 tok/s 68 tok/s -4% 16.0 GB LM Studio community 2026-01-03
Qwen 2.5 7B Qwen 2.5 7B FP16 63 tok/s 65 tok/s -3% 20.1 GB Xybrid CLI community 2026-03-01
🧠 DeepSeek R1 Distill 7B FP16 61 tok/s 65 tok/s -6% 18.0 GB Ollama community 2026-03-17
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 60 tok/s 62 tok/s -3% 19.3 GB Xybrid CLI community 2026-05-14
LFM2.5 8B A1B LFM2.5 8B A1B FP16 56 tok/s 61 tok/s -8% 20.6 GB Jan community 2026-02-23
Qwen 3.5 9B Qwen 3.5 9B FP16 54 tok/s 54 tok/s +0% 22.6 GB LM Studio community 2026-02-27
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q4 53 tok/s 50 tok/s +6% 23.9 GB Jan community 2026-02-10
🧠 Qwen3 8B FP16 53 tok/s 60 tok/s -12% 20.2 GB LM Studio community 2026-04-19
Gemma 4 26B A4B Gemma 4 26B A4B Q6 52 tok/s 48 tok/s +8% 23.4 GB LM Studio editorial 2026-02-10
👨‍💻 Laguna XS.2 Q4 51 tok/s 53 tok/s -4% 21.5 GB Xybrid CLI editorial 2026-03-27
Gemma 4 31B Gemma 4 31B Q5 48 tok/s 48 tok/s +0% 24.9 GB Jan community 2026-04-21
Qwen3 Coder Next Qwen3 Coder Next Q3 26 tok/s 28 tok/s -7% 45.9 GB Jan community 2026-03-01
Llama 4 Scout Llama 4 Scout Q2 1 tok/s 1 tok/s +0% 50.1 GB LM Studio community 2026-01-14
← All benchmarks