AI Benchmarks

bonsai-27b-pq2-agent-benchmark-en-cover

7.2GB 27B Agent Benchmark: Bonsai 2 PQ2_0

玩客 September 20, 2026

Can a 7.2GB 27B model handle real code-agent work?...

cover_7900xtx_125b_1789563895884

Qwen 3.8 125B MoE on Dual RX 7900 XTX: 48K Context at 28 Tok/s Benchmark & Guide

玩客 September 18, 2026

Benchmark & deployment guide for Qwen 3.8 125B on...

dual-rx-7900-xtx-qwen38-27b-cover-en

Deploying Qwen3.8-27B on Dual RX 7900 XTX: Dual Independent 256K Context at 114 Tokens/s (Ubuntu 24.04 + ROCm + llama.cpp)

玩客 September 14, 2026

How to deploy Qwen3.8-27B across dual AMD Radeon RX...

rtx-3060-12gb-qwen38-27b-cover-en

Running Qwen 3.8 27B on RTX 3060 12GB: 64K Context at 22 Tokens/s (Ubuntu 24.04 + revv / llama.cpp)

玩客 September 14, 2026

Running Qwen 3.8 27B on RTX 3060 12GB: 64K...

qwen-3-8-27b-7900xtx-53tps-cover

Deploy Qwen 3.8 27B on AMD Radeon RX 7900 XTX: Squeezing 53 TPS with 262K Context & KV Cache Q4

玩客 September 4, 2026

Deploy Qwen 3.8 27B on AMD Radeon RX 7900...