Year: 2026

ep20-x99-3060-125b-cover

Running a 125B AI on a 12GB RTX 3060: X99 Benchmark & Tuning Guide

玩客 November 10, 2026

Can an entry-level 12GB RTX 3060 run a 125B...

ep19-rtx3060-125b-cover

RTX 3060 12GB Runs a 125B AI Model: Complete Speedy Setup Guide for Ubuntu

玩客 November 8, 2026

RTX 3060 12GB Runs a 125B AI Model: Complete...

rtx3080-10gb-125b-speedy-benchmark-en-cover

Running a 125B MoE Model on a 10GB RTX 3080: Speedy 94.6 tok/s & PCIe 4.0 x16 Benchmark Guide

玩客 November 7, 2026

Bare-metal benchmark and 4-step guide for running Qwen3.8-Flash-Next 125B...

hero-en-performance-showcase

Dual RX 7900 XTX Deployment Guide: Run a 125B MoE Model with 256K Context at 5,748 tok/s

玩客 November 4, 2026

Complete deployment walkthrough for serving a 125B MoE model...

rx-7900-xtx-125b-strata-benchmark-en-cover

Running 125B MoE at 200 Tokens/s on a Single 24GB GPU: AMD RX 7900 XTX + Strata Benchmark Guide

玩客 November 2, 2026

Running 125B MoE at 200 Tokens/s on a Single...

ep06-en-cover-primary

Running 125B MoE on a GPU: RTX 3060 12GB + Strata 3-Tier Storage Guide

玩客 October 14, 2026

Engineering guide: run Qwen 3.8 125B MoE at 128K...

cover

125B MoE vs 27B Dense on Dual RX 7900 XTX: The 3X Speed Trap & Real Code Verification

玩客 October 10, 2026

125B MoE vs 27B Dense on Dual RX 7900...

cover_125b_vs_27b_en

125B vs 27B Real Showdown: Coding Benchmark & MoE Trade-offs on Dual RX 7900 XTX

玩客 October 9, 2026

Real-world coding and token processing benchmark comparing 125B MoE...

strata_rx7900xtx_cover_en

Running a 90GB MoE Model on a Single 24GB GPU: Strata & RX 7900 XTX 128K Guide

玩客 October 8, 2026

Running a 90GB MoE Model on a Single 24GB...

cover_a_7900xtx_speed

Single RX 7900 XTX: Tune 84GB Qwen3.8-Flash-Next to 1,320 tok/s Prefill

玩客 October 3, 2026

Comprehensive engineering guide to running 84GB Qwen3.8-Flash-Next on a...