Gaming PC (RX 7800 XT) 32GB

Windows Ultra tier · AMD Ryzen 7 · 32 GB RAM · 624 GB/s bandwidth
View device page →
BENCHMARK RESULTS (71)
Model Quant Measured Estimated RAM used App Source Date
SmolLM2 360M SmolLM2 360M FP16 223 tok/s 200 tok/s +12% 1.2 GB Xybrid CLI editorial 2026-04-02
Ternary Bonsai 8B Ternary Bonsai 8B Q2 223 tok/s 200 tok/s +12% 1.8 GB Jan community 2026-04-07
Whisper Large V3 Whisper Large V3 FP16 223 tok/s 200 tok/s +12% 3.5 GB Xybrid CLI editorial 2026-03-13
Qwen 3.5 0.8B Qwen 3.5 0.8B FP16 222 tok/s 200 tok/s +11% 2.0 GB Xybrid CLI editorial 2026-02-09
Qwen 2.5 Coder 0.5B Qwen 2.5 Coder 0.5B FP16 222 tok/s 200 tok/s +11% 1.3 GB LM Studio community 2026-01-06
🔢 BGE Small FP16 222 tok/s 200 tok/s +11% 0.1 GB LM Studio community 2026-01-06
🔢 all-MiniLM-L6-v2 FP16 219 tok/s 200 tok/s +10% 0.1 GB Xybrid CLI community 2026-02-07
Bonsai Image 4B Bonsai Image 4B Q2 219 tok/s 200 tok/s +10% 2.1 GB Xybrid CLI community 2026-04-19
Bonsai 8B (1-bit) Bonsai 8B (1-bit) Q1 218 tok/s 200 tok/s +9% 1.2 GB Ollama community 2026-04-06
Whisper Tiny Whisper Tiny FP16 218 tok/s 200 tok/s +9% 0.1 GB Xybrid CLI community 2026-03-01
🎨 Stable Diffusion Turbo FP16 217 tok/s 200 tok/s +9% 2.3 GB Xybrid CLI community 2026-05-28
Gemma 3 1B Gemma 3 1B FP16 213 tok/s 200 tok/s +7% 2.8 GB Xybrid CLI community 2026-05-26
Llama 3.2 1B Llama 3.2 1B FP16 209 tok/s 200 tok/s +5% 3.1 GB LM Studio editorial 2026-01-16
🗣️ NeuTTS Air FP16 206 tok/s 200 tok/s +3% 1.6 GB Xybrid CLI community 2026-05-25
Whisper Medium Whisper Medium FP16 206 tok/s 200 tok/s +3% 1.7 GB Xybrid CLI editorial 2026-04-05
LFM2.5 1.2B LFM2.5 1.2B FP16 205 tok/s 200 tok/s +3% 2.7 GB LM Studio editorial 2026-01-14
🧠 DeepSeek R1 Distill 1.5B FP16 205 tok/s 189 tok/s +8% 3.9 GB Jan community 2026-04-18
Ternary Bonsai 4B Ternary Bonsai 4B Q2 203 tok/s 200 tok/s +2% 0.9 GB Jan community 2026-03-13
🗣️ KittenTTS Nano FP16 200 tok/s 200 tok/s +0% 0.1 GB Piper editorial 2026-05-11
🗣️ Dia 1.6B FP16 197 tok/s 189 tok/s +4% 4.2 GB Xybrid CLI community 2026-04-23
🔢 Nomic Embed Text FP16 195 tok/s 200 tok/s -2% 0.3 GB Ollama community 2026-03-16
StableLM 2 1.6B StableLM 2 1.6B FP16 194 tok/s 189 tok/s +3% 4.1 GB Jan community 2026-04-21
Qwen 2.5 0.5B Qwen 2.5 0.5B FP16 190 tok/s 200 tok/s -5% 1.5 GB Ollama community 2026-04-21
Qwen 2.5 Coder 1.5B Qwen 2.5 Coder 1.5B FP16 190 tok/s 195 tok/s -3% 3.8 GB Xybrid CLI community 2026-02-24
SmolLM2 1.7B SmolLM2 1.7B FP16 187 tok/s 184 tok/s +2% 3.9 GB Ollama community 2026-01-04
🗣️ OuteTTS 0.3 500M FP16 187 tok/s 200 tok/s -6% 1.1 GB Piper community 2026-01-28
🔢 GTE Large FP16 186 tok/s 200 tok/s -7% 0.7 GB Ollama editorial 2026-03-04
TinyLlama 1.1B TinyLlama 1.1B FP16 184 tok/s 200 tok/s -8% 2.6 GB LM Studio community 2026-03-15
Whisper Small Whisper Small FP16 183 tok/s 200 tok/s -8% 0.6 GB Xybrid CLI editorial 2026-03-17
🎙️ Distil-Whisper Large V3 FP16 182 tok/s 200 tok/s -9% 1.8 GB Xybrid CLI community 2026-03-16
🗣️ Kokoro 82M FP16 181 tok/s 200 tok/s -9% 0.4 GB Xybrid CLI community 2026-04-07
Wav2Vec2 Base Wav2Vec2 Base FP16 181 tok/s 200 tok/s -9% 0.3 GB Xybrid CLI community 2026-02-10
Ternary Bonsai 1.7B Ternary Bonsai 1.7B Q2 180 tok/s 200 tok/s -10% 0.4 GB Jan community 2026-05-16
🗣️ KittenTTS Mini FP16 180 tok/s 200 tok/s -10% 0.2 GB Xybrid CLI community 2026-03-27
👁️ SmolVLM 500M FP16 178 tok/s 200 tok/s -11% 1.3 GB LM Studio community 2026-04-20
SmolLM2 135M SmolLM2 135M FP16 177 tok/s 200 tok/s -11% 0.3 GB Ollama community 2026-05-11
👁️ Moondream 2B FP16 159 tok/s 169 tok/s -6% 4.7 GB LM Studio editorial 2026-01-01
Gemma 4 E2B Gemma 4 E2B FP16 146 tok/s 139 tok/s +5% 5.1 GB Jan community 2026-03-16
Qwen 3.5 2B Qwen 3.5 2B FP16 144 tok/s 149 tok/s -3% 5.0 GB Ollama community 2026-04-20
🎨 Stable Diffusion 3.5 Medium FP16 140 tok/s 136 tok/s +3% 5.1 GB Jan community 2026-02-08
👨‍💻 StarCoder2 3B FP16 104 tok/s 101 tok/s +3% 6.9 GB Jan community 2026-02-08
Qwen 2.5 Coder 3B Qwen 2.5 Coder 3B FP16 102 tok/s 98 tok/s +4% 6.8 GB Xybrid CLI community 2026-01-03
Qwen 2.5 3B Qwen 2.5 3B FP16 97 tok/s 98 tok/s -1% 6.9 GB LM Studio community 2026-04-04
🎨 SDXL Turbo FP16 95 tok/s 96 tok/s -1% 8.2 GB Ollama community 2026-04-23
Llama 3.2 3B Llama 3.2 3B FP16 94 tok/s 95 tok/s -1% 7.7 GB Ollama community 2026-04-23
Qwen 2.5 7B Qwen 2.5 7B Q8 86 tok/s 77 tok/s +12% 9.2 GB LM Studio editorial 2026-03-13
Qwen 3.5 4B Qwen 3.5 4B FP16 81 tok/s 76 tok/s +7% 8.9 GB Xybrid CLI community 2026-01-01
Phi-4 Mini Phi-4 Mini FP16 81 tok/s 80 tok/s +1% 8.5 GB Ollama community 2026-02-09
Llama 3.1 8B Llama 3.1 8B Q8 78 tok/s 73 tok/s +7% 9.2 GB Xybrid CLI community 2026-01-03
🧠 DeepSeek R1 Distill 8B Q8 78 tok/s 73 tok/s +7% 9.8 GB Xybrid CLI community 2026-03-13
Mistral 7B Mistral 7B Q8 77 tok/s 76 tok/s +1% 9.3 GB Xybrid CLI editorial 2026-05-10
Qwen 2.5 Coder 7B Qwen 2.5 Coder 7B Q8 73 tok/s 77 tok/s -5% 10.4 GB Xybrid CLI community 2026-03-27
Qwen 2.5 VL 7B Qwen 2.5 VL 7B Q8 73 tok/s 73 tok/s +0% 9.2 GB Ollama community 2026-02-08
🧠 DeepSeek R1 Distill 7B Q8 72 tok/s 77 tok/s -6% 10.2 GB Jan community 2026-02-22
Qwen 3.5 9B Qwen 3.5 9B Q8 71 tok/s 64 tok/s +11% 12.0 GB Xybrid CLI community 2026-04-18
Gemma 3 4B Gemma 3 4B FP16 70 tok/s 70 tok/s +0% 10.0 GB Ollama community 2026-01-02
Gemma 3n E2B Gemma 3n E2B FP16 69 tok/s 70 tok/s -1% 9.5 GB Xybrid CLI community 2026-04-06
Gemma 4 E4B Gemma 4 E4B FP16 68 tok/s 69 tok/s -1% 10.0 GB Ollama community 2026-01-28
Phi-4 Medium Phi-4 Medium Q6 65 tok/s 58 tok/s +12% 11.9 GB Ollama community 2026-03-04
LFM2.5 8B A1B LFM2.5 8B A1B Q8 63 tok/s 71 tok/s -11% 10.6 GB Jan community 2026-03-25
🧠 Qwen3 8B Q8 63 tok/s 72 tok/s -12% 10.9 GB Xybrid CLI editorial 2026-05-25
Gemma 3n E4B Gemma 3n E4B FP16 51 tok/s 46 tok/s +11% 17.0 GB Jan community 2026-02-18
Qwen 3.5 35B A3B Qwen 3.5 35B A3B Q2 49 tok/s 52 tok/s -6% 13.9 GB Jan community 2026-05-16
👨‍💻 DeepSeek Coder 6.7B FP16 49 tok/s 46 tok/s +7% 17.7 GB Xybrid CLI community 2026-01-06
Gemma 4 26B A4B Gemma 4 26B A4B Q3 48 tok/s 50 tok/s -4% 14.9 GB Ollama community 2026-03-17
🎨 FLUX.1 Schnell Q8 48 tok/s 49 tok/s -2% 15.7 GB Jan community 2026-04-18
Mistral Nemo 12B Mistral Nemo 12B Q8 44 tok/s 48 tok/s -8% 14.6 GB LM Studio editorial 2026-02-10
Gemma 3 12B Gemma 3 12B Q8 43 tok/s 48 tok/s -10% 15.1 GB LM Studio community 2026-03-15
Gemma 4 31B Gemma 4 31B Q3 43 tok/s 46 tok/s -7% 16.3 GB Ollama community 2026-04-20
👨‍💻 Laguna XS.2 Q3 43 tok/s 45 tok/s -4% 17.0 GB Ollama community 2026-04-18
👁️ LLaVA 1.6 7B FP16 41 tok/s 44 tok/s -7% 17.2 GB LM Studio community 2026-03-17
← All benchmarks