News

Latest news and updates on local artificial intelligence

All categories Model releases Decision models AI agents Tools & releases Hardware & accelerators On-device & edge Use cases Research Safety Benchmarks

1 news item in Benchmarks

BenchLM publishes its September ranking of the best local LLMs: VRAM defines the tiers

September 27, 2026

Benchmarks

The September 2026 ranking orders Open-weight models by VRAM tier: GPT-OSS 20B and ZAYA1-8B lead the 8-16 GB tier, Qwen3.6-27B (46.49) and Gemma 4 31B (44.84) dominate the 16-24 GB tier on a single RTX 4090 at Q4, and trillion-Parameter MoEs need 8x H100. A useful reference when choosing a model size for your hardware.