Redis creator releases ds4 local LLM inference engine

The creator of Redis released ds4, a narrow C inference engine that runs frontier open-weight models such as DeepSeek V4, GLM 5.x and Qwen3.8 locally on high-memory Macs and CUDA/ROCm machines. MIT-licensed, it bundles a CLI, HTTP APIs and a native agent, using asymmetric quantization to make MoE models practical locally, with roughly 34.4 T/s generation and 557 T/s prefill on a 128GB Mac.

• Developer launches open-source local AI model leaderboard2026-10-12
• BAAI Releases AREX-2: 27B Long-Horizon Agent Model2026-10-01
• Qwen3.8 runs locally at 51 t/s on 12GB laptop GPU2026-09-30
• User claims merging Qwen3.6 and 3.8 27B boosts generation efficiency2026-09-29
• Qwen3.8 27B IQ3_XXS vs Bonsai Ternary PQ2 quantization test2026-09-20