Ai4Users.comLocal AI & LLM community
Sign in to contributeSign in

Local AI hardware: ET900N G3

Hardware profile
Hardware Memory Bandwidth Computing power vLLM
ET900N G3ASUS ExpertCenter Pro ET900N G3 with NVIDIA GB300 Grace Blackwell Ultra 748 GBCoherent Memory 7100 GB/s ~20000 TOPS yes
Compatible models Estimated speeds, not benchmark results: calculated from memory bandwidth and model size. Real results can differ significantly because there is no precise formula for deriving LLM generation speed from hardware specifications alone.
Model Size Approx. Q4 memory Estimated generation
MiMo V2.5 ProMoE 1020Bactive 42B 612 GB 100 tok/s4-bit quantization
Kimi K2.6MoE 1000Bactive 32B 600 GB 125 tok/s4-bit quantization
Kimi K2.7MoE 1000Bactive 32B 600 GB 125 tok/s4-bit quantization
Hy4MoE 770Bactive 49B 462 GB 88 tok/s4-bit quantization
GLM 5.1MoE 744Bactive 40B 446.4 GB 104 tok/s4-bit quantization
GLM 5.2MoE 744Bactive 40B 446.4 GB 104 tok/s4-bit quantization
DeepSeek V4.1 FlashMoE 552Bactive 16B 331.2 GB 211 tok/s4-bit quantization
Nemotron 3 UltraMoE 550Bactive 55B 330 GB 79 tok/s4-bit quantization
Qwen 3 Coder 480BMoE 480Bactive 35B 288 GB 117 tok/s4-bit quantization
MiniMax M3MoE 428Bactive 23B 256.8 GB 163 tok/s4-bit quantization
Ornith 1.5 397BMoE 397Bactive 17B 238.2 GB 203 tok/s4-bit quantization
Qwen 3.5 397BMoE 397Bactive 17B 238.2 GB 203 tok/s4-bit quantization
GLM 5.3 FlashMoE 320Bactive 18B 192 GB 195 tok/s4-bit quantization
MiMo V2.5MoE 310Bactive 15B 186 GB 221 tok/s4-bit quantization
Hy3MoE 295Bactive 21B 177 GB 174 tok/s4-bit quantization
DeepSeek V4 FlashMoE 284Bactive 13B 170.4 GB 242 tok/s4-bit quantization
Inkling SmallMoE 276Bactive 12B 165.6 GB 255 tok/s4-bit quantization
Solar Open 2MoE 250Bactive 15B 150 GB 221 tok/s4-bit quantization
Qwen 3 235BMoE 235Bactive 22B 141 GB 168 tok/s4-bit quantization
Laguna M.1MoE 225Bactive 23B 135 GB 163 tok/s4-bit quantization
Command A+MoE 218Bactive 25B 130.8 GB 153 tok/s4-bit quantization
Step 3.7 FlashMoE 198Bactive 11B 118.8 GB 269 tok/s4-bit quantization
Mistral Medium 3.5Dense 128B 76.8 GB 48 tok/s4-bit quantization
Qwen 3.8 Flash NextMoE 125Bactive 6B 75 GB 369 tok/s4-bit quantization
Ling 3.0 Flash VLMoE 124Bactive 5.5B 74.4 GB 383 tok/s4-bit quantization
Ling 3.0 FlashMoE 124Bactive 5.1B 74.4 GB 395 tok/s4-bit quantization
Qwen 3.5 122BMoE 122Bactive 10B 73.2 GB 284 tok/s4-bit quantization
Nemotron 3 SuperMoE 120Bactive 12B 72 GB 255 tok/s4-bit quantization
Mistral Small 4MoE 119Bactive 6.5B 71.4 GB 356 tok/s4-bit quantization
Laguna S 2.1MoE 118Bactive 8B 70.8 GB 321 tok/s4-bit quantization
GPT-OSS 120BMoE 116.8Bactive 5.1B 70.1 GB 395 tok/s4-bit quantization
Sarvam 105BMoE 105Bactive 10.3B 63 GB 279 tok/s4-bit quantization
Qwen 3 Coder Next 80BMoE 80Bactive 3B 48 GB 475 tok/s4-bit quantization
Ornith 1.0 35BMoE 35Bactive 3B 21 GB 475 tok/s4-bit quantization
Ornith 1.5 35BMoE 35Bactive 3B 21 GB 475 tok/s4-bit quantization
Qwen 3.6 35BMoE 35Bactive 3B 21 GB 475 tok/s4-bit quantization
Laguna XS 2.1MoE 33Bactive 3B 19.8 GB 475 tok/s4-bit quantization
Qwen 2.5 32BDense 32.5B 19.5 GB 174 tok/s4-bit quantization
Gemma 4 31BDense 31B 18.6 GB 181 tok/s4-bit quantization
Qwen 3 Coder 30BMoE 30.5Bactive 3.3B 18.3 GB 462 tok/s4-bit quantization
Granite 4.1 30BDense 30B 18 GB 186 tok/s4-bit quantization
Granite 4.2 30BDense 30B 18 GB 186 tok/s4-bit quantization
Muse GlimmerDense 30B 18 GB 186 tok/s4-bit quantization
GLM 4.7 FlashMoE 30Bactive 3B 18 GB 475 tok/s4-bit quantization
Nemotron 3.5 LightningMoE 30Bactive 3B 18 GB 475 tok/s4-bit quantization
Fara 1.5 27BDense 27B 16.2 GB 204 tok/s4-bit quantization
Qwen 3.6 27BDense 27B 16.2 GB 204 tok/s4-bit quantization
Qwen 3.8 27BDense 27B 16.2 GB 204 tok/s4-bit quantization
Gemma 4 26BMoE 26Bactive 4B 15.6 GB 433 tok/s4-bit quantization
GPT-OSS 20BMoE 20.9Bactive 3.6B 12.5 GB 449 tok/s4-bit quantization
Instella-MoE 16B ThinkMoE 16Bactive 2.8B 9.6 GB 484 tok/s4-bit quantization
Qwen 3 14BDense 14B 8.4 GB 344 tok/s4-bit quantization
Gemma 3 12BDense 12B 7.2 GB 385 tok/s4-bit quantization
Gemma 4 12BDense 12B 7.2 GB 385 tok/s4-bit quantization
Fara 1.5 9BDense 9B 5.4 GB 468 tok/s4-bit quantization
Ornith 1.0 9BDense 9B 5.4 GB 468 tok/s4-bit quantization
Ornith 1.5 9BDense 9B 5.4 GB 468 tok/s4-bit quantization
Qwen 3.5 9BDense 9B 5.4 GB 468 tok/s4-bit quantization
Qwythos 9BDense 9B 5.4 GB 468 tok/s4-bit quantization
Granite 4.1 8BDense 8B 4.8 GB 505 tok/s4-bit quantization
Granite 4.2 8BDense 8B 4.8 GB 505 tok/s4-bit quantization
Qwen 3 8BDense 8B 4.8 GB 505 tok/s4-bit quantization
Ling 3.0 TinyMoE 7.9Bactive 1.3B 4.7 GB 567 tok/s4-bit quantization
Fara 1.5 4BDense 4B 2.4 GB 732 tok/s4-bit quantization
Gemma 3 4BDense 4B 2.4 GB 732 tok/s4-bit quantization
Qwen 3 4B Instruct 2507Dense 4B 2.4 GB 732 tok/s4-bit quantization
Qwen 3.5 4BDense 4B 2.4 GB 732 tok/s4-bit quantization
Spark X2.5 4BDense 4B 2.4 GB 732 tok/s4-bit quantization
Granite 4.1 3BDense 3B 1.8 GB 825 tok/s4-bit quantization
Granite 4.2 3BDense 3B 1.8 GB 825 tok/s4-bit quantization
Llama 3.2 3B InstructDense 3B 1.8 GB 825 tok/s4-bit quantization
Ministral 3 3BDense 3B 1.8 GB 825 tok/s4-bit quantization
Nanbeige 4.2 3BDense 3B 1.8 GB 825 tok/s4-bit quantization
2 videos found Showing 1-2

Ai4Users.com

Copyright © 2026 Piotr Szawdyński. All rights reserved.