Qwen 3.8 27B praised as best self-hosted single-shot output; dev eyes home LLM rig
gregbarbosa · x · 2026-08-15
Developer @greatscottdev showed that Qwen 3.8 27B produced the best single-shot output he has seen from any model he self-hosts.
Quoting the post, Greg Barbosa said it makes him want to finally build out his own home local LLM setup — a sign of local deployment's pull as open models close the quality gap.
More from Infra
- User runs Krea2 and MiniMax Music locally — -becausereasons- · 2026-08-17
- MiniMax H3 Video Generation Tested on RTX 3060 12GB — solomars3 · 2026-08-17
- SayGM Launches TEE-Verified AI Gateway on Bittensor — markjeffrey · 2026-08-17
- Score Studio enables local inference with decentralized storage — markjeffrey · 2026-08-17
- Nvidia to Invest Up to $3B in Lancium, Owner of Stargate Campus Power Infra — Beth_Kindig · 2026-08-17
- Bun's Web APIs get up to 4x faster in next version — ctjlewis · 2026-08-17