Gaming PC (RX 7900 XTX) 64GB

Windows Ultra tier · AMD Ryzen 9 · 64 GB RAM · 960 GB/s bandwidth
View device page →
BENCHMARK RESULTS (73)
Model Quant Measured Estimated RAM used App Source Date
🗣️ Dia 1.6B FP16 224 tok/s 200 tok/s +12% 4.0 GB Xybrid CLI community 2026-04-19
🗣️ KittenTTS Mini FP16 223 tok/s 200 tok/s +12% 0.2 GB Piper community 2026-03-04
🔢 GTE Large FP16 222 tok/s 200 tok/s +11% 0.7 GB Jan community 2026-04-06
LFM2.5 1.2B LFM2.5 1.2B FP16 220 tok/s 200 tok/s +10% 2.5 GB Ollama community 2026-04-08
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 216 tok/s 200 tok/s +8% 3.4 GB Xybrid CLI community 2026-01-03
TinyLlama 1.1B TinyLlama 1.1B FP16 215 tok/s 200 tok/s +8% 2.3 GB Ollama community 2026-04-08
🎙️ Distil-Whisper Large V3 FP16 215 tok/s 200 tok/s +8% 1.6 GB Xybrid CLI community 2026-03-02
🔢 Nomic Embed Text FP16 213 tok/s 200 tok/s +7% 0.3 GB Ollama editorial 2026-04-07
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 212 tok/s 200 tok/s +6% 1.4 GB Jan community 2026-02-09
Gemma 4 E2B Gemma 4 E2B FP16 210 tok/s 200 tok/s +5% 5.3 GB LM Studio community 2026-05-08
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 208 tok/s 200 tok/s +4% 1.3 GB LM Studio editorial 2026-05-12
🎨 Stable Diffusion 3.5 Medium FP16 208 tok/s 200 tok/s +4% 5.2 GB LM Studio editorial 2026-01-15
Wav2Vec2 Base Wav2Vec2 Base FP16 208 tok/s 200 tok/s +4% 0.3 GB Whisper Transcription community 2026-02-07
👁️ SmolVLM 500M FP16 207 tok/s 200 tok/s +4% 1.2 GB LM Studio editorial 2026-04-06
🗣️ NeuTTS Air FP16 207 tok/s 200 tok/s +4% 1.7 GB Xybrid CLI community 2026-02-06
Qwen 3.5 2B Qwen 3.5 2B FP16 206 tok/s 200 tok/s +3% 5.5 GB LM Studio community 2026-01-22
🔢 BGE Small FP16 206 tok/s 200 tok/s +3% 0.1 GB Jan community 2026-02-08
Whisper Large V3 Whisper Large V3 FP16 206 tok/s 200 tok/s +3% 4.0 GB Xybrid CLI editorial 2026-01-22
Llama 3.2 1B Llama 3.2 1B FP16 204 tok/s 200 tok/s +2% 3.4 GB LM Studio editorial 2026-02-26
Whisper Small Whisper Small FP16 203 tok/s 200 tok/s +2% 0.5 GB Whisper Transcription community 2026-03-12
👁️ Moondream 2B FP16 202 tok/s 200 tok/s +1% 4.6 GB Jan community 2026-05-28
SmolLM2 135M SmolLM2 135M FP16 200 tok/s 200 tok/s +0% 0.3 GB Jan community 2026-04-21
StableLM 2 1.6B StableLM 2 1.6B FP16 199 tok/s 200 tok/s +0% 3.6 GB Ollama community 2026-02-10
Ternary Bonsai 4B Ternary Bonsai 4B Q2 198 tok/s 200 tok/s -1% 1.1 GB Jan community 2026-04-20
🧠 DeepSeek R1 Distill 1.5B FP16 197 tok/s 200 tok/s -1% 3.5 GB Xybrid CLI community 2026-05-09
Ternary Bonsai 8B Ternary Bonsai 8B Q2 196 tok/s 200 tok/s -2% 2.0 GB Jan community 2026-05-25
SmolLM2 1.7B SmolLM2 1.7B FP16 192 tok/s 200 tok/s -4% 4.0 GB Ollama community 2026-03-17
🗣️ KittenTTS Nano FP16 192 tok/s 200 tok/s -4% 0.1 GB Piper community 2026-02-15
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 186 tok/s 200 tok/s -7% 2.3 GB LM Studio community 2026-05-28
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 183 tok/s 200 tok/s -8% 1.4 GB Jan community 2026-05-14
Whisper Tiny Whisper Tiny FP16 183 tok/s 200 tok/s -8% 0.1 GB Whisper Transcription community 2026-03-01
Whisper Medium Whisper Medium FP16 183 tok/s 200 tok/s -8% 1.8 GB Whisper Transcription community 2026-01-17
Bonsai Image 4B Bonsai Image 4B Q2 182 tok/s 200 tok/s -9% 2.3 GB Jan community 2026-03-25
Gemma 3 1B Gemma 3 1B FP16 180 tok/s 200 tok/s -10% 2.7 GB Xybrid CLI community 2026-05-24
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 180 tok/s 200 tok/s -10% 0.5 GB Jan community 2026-03-27
🔢 all-MiniLM-L6-v2 FP16 180 tok/s 200 tok/s -10% 0.1 GB LM Studio editorial 2026-04-21
🎨 Stable Diffusion Turbo FP16 180 tok/s 200 tok/s -10% 2.6 GB LM Studio community 2026-04-21
🗣️ Kokoro 82M FP16 180 tok/s 200 tok/s -10% 0.4 GB Piper editorial 2026-03-15
🗣️ OuteTTS 0.3 500M FP16 178 tok/s 200 tok/s -11% 1.1 GB Piper community 2026-01-06
SmolLM2 360M SmolLM2 360M FP16 176 tok/s 200 tok/s -12% 1.1 GB Jan community 2026-02-19
Qwen 2.5 3B Qwen 2.5 3B FP16 168 tok/s 150 tok/s +12% 7.7 GB Xybrid CLI community 2026-04-19
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 165 tok/s 150 tok/s +10% 7.2 GB Ollama community 2026-04-10
👨‍💻 StarCoder2 3B FP16 144 tok/s 155 tok/s -7% 8.0 GB Jan community 2026-04-02
Llama 3.2 3B Llama 3.2 3B FP16 134 tok/s 145 tok/s -8% 7.9 GB Xybrid CLI community 2026-01-18
🎨 SDXL Turbo FP16 131 tok/s 148 tok/s -11% 8.2 GB LM Studio editorial 2026-05-26
Gemma 4 E4B Gemma 4 E4B FP16 119 tok/s 107 tok/s +11% 11.1 GB Ollama community 2026-02-24
Qwen 3.5 4B Qwen 3.5 4B FP16 114 tok/s 117 tok/s -3% 9.8 GB Xybrid CLI community 2026-02-24
Gemma 3n E2B Gemma 3n E2B FP16 112 tok/s 108 tok/s +4% 9.4 GB LM Studio community 2026-03-01
Phi-4 Mini Phi-4 Mini FP16 111 tok/s 123 tok/s -10% 9.9 GB Jan community 2026-02-18
Gemma 3 4B Gemma 3 4B FP16 103 tok/s 108 tok/s -5% 9.6 GB Xybrid CLI community 2026-04-03
Mistral Nemo 12B Mistral Nemo 12B Q8 82 tok/s 74 tok/s +11% 14.0 GB Ollama community 2026-03-02
Gemma 3 12B Gemma 3 12B Q8 75 tok/s 74 tok/s +1% 15.3 GB Ollama community 2026-02-19
👁️ LLaVA 1.6 7B FP16 74 tok/s 67 tok/s +10% 16.1 GB Ollama community 2026-03-02
Gemma 3n E4B Gemma 3n E4B FP16 72 tok/s 70 tok/s +3% 17.1 GB LM Studio editorial 2026-02-24
Phi-4 Medium Phi-4 Medium Q8 71 tok/s 65 tok/s +9% 18.0 GB Ollama community 2026-05-12
🎨 FLUX.1 Schnell Q8 71 tok/s 76 tok/s -7% 16.1 GB LM Studio editorial 2026-01-04
🧠 DeepSeek R1 Distill 7B FP16 65 tok/s 62 tok/s +5% 16.6 GB Ollama community 2026-03-05
🧠 DeepSeek R1 Distill 8B FP16 65 tok/s 60 tok/s +8% 19.0 GB Ollama community 2026-02-19
Qwen 2.5 7B Qwen 2.5 7B FP16 64 tok/s 62 tok/s +3% 17.3 GB Jan community 2026-03-14
👨‍💻 DeepSeek Coder 6.7B FP16 64 tok/s 70 tok/s -9% 17.5 GB LM Studio editorial 2026-05-28
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B FP16 60 tok/s 62 tok/s -3% 17.8 GB Xybrid CLI community 2026-01-17
Qwen 2.5 VL 7B Qwen 2.5 VL 7B FP16 60 tok/s 59 tok/s +2% 20.8 GB Jan community 2026-05-01
Mistral 7B Mistral 7B FP16 59 tok/s 65 tok/s -9% 17.3 GB Jan community 2026-05-11
LFM2.5 8B A1B LFM2.5 8B A1B FP16 58 tok/s 58 tok/s +0% 18.1 GB Ollama community 2026-02-08
Llama 3.1 8B Llama 3.1 8B FP16 56 tok/s 60 tok/s -7% 18.6 GB Xybrid CLI community 2026-01-19
🧠 Qwen3 8B FP16 54 tok/s 57 tok/s -5% 21.2 GB Jan community 2026-02-23
Qwen 3.5 9B Qwen 3.5 9B FP16 53 tok/s 52 tok/s +2% 23.9 GB Jan community 2026-01-02
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q4 53 tok/s 48 tok/s +10% 24.7 GB Ollama community 2026-01-18
👨‍💻 Laguna XS.2 Q4 53 tok/s 51 tok/s +4% 21.4 GB Jan community 2026-02-10
Gemma 4 26B A4B Gemma 4 26B A4B Q6 51 tok/s 46 tok/s +11% 25.3 GB Xybrid CLI community 2026-04-21
Gemma 4 31B Gemma 4 31B Q5 43 tok/s 46 tok/s -7% 26.7 GB LM Studio editorial 2026-01-01
Qwen3 Coder Next Qwen3 Coder Next Q3 26 tok/s 27 tok/s -4% 43.9 GB Xybrid CLI community 2026-01-22
Llama 4 Scout Llama 4 Scout Q2 1 tok/s 1 tok/s +0% 48.6 GB Jan community 2026-02-06
← All benchmarks