3h ago
••
Latest News
Latest news from Subscribe to LocalLLaMA's sources
3h ago
Qwen3.5-9B-Claude-4.6-Opus-Uncensored-Distilled-GGUF
3h ago
Help needed for GENOAD8X-2T/BCM + Epyc 9135 build. Won’t POST
3h ago
AMD HBCC Support
4h ago
Turnstone, better (and safer IMO) OpenClaw for DevOps and Sysadmin
4h ago
GLM 4.7 on dual RTX Pro 6000 Blackwell
6h ago
What does everyone's local agentic workflow look like?
6h ago
[RELEASE] New model - Apex 1.6 Instruct 350M - my most powerful chat model 🚀
6h ago
Would you use a private AI search for your phone?
6h ago
Built a Cursor alternative that works with any model including local ones — and now trying to integrate African-built LLMs as first-class providers
6h ago
SILMA TTS Release: A new lightweight (150m), open-source bilingual Text-to-Speech model
7h ago
Setting Up Qwen3.5-27B Locally: Tips and a Recipe for Smooth Runs
7h ago
Dialogue generation with Qwen TTS
7h ago
Homelab has paid for itself! (at least this is how I justify it...)
8h ago
People Trust AI more than humans
8h ago
Benchmark: ik_llama.cpp vs llama.cpp on Qwen3/3.5 MoE Models
8h ago
The Fast Food Problem with AI Coding
8h ago
Qwen 27B works GREAT as a LORE MASTER!
8h ago
Are there any alternatives to ShareGPT
8h ago