Reach 125K+ monthly visitors
Advertise on TrendshiftLocal LLM
Run Clark Air Sana 1.6B (ternary ~1.58-bit, GemLite INT2) natively under ComfyUI's KSampler
RLM-first backend for the Pi coding agent: a small local model writes code, runs it, verifies, and iterates. Code generation first, with exact data-beyond-context as a second capability.
Local-first, self-hosted home & records assistant: one LLM brain, scoped tools, durable memory. AGPL-3.0.
Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.
A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider
Serverless-GPU LLM serving: scale-to-zero with fast GPU snapshot/restore (cuda-checkpoint), multi-tenant packing, and an OpenAI-compatible API — built on vLLM.
Brainstorm System design with an intelligent agent.
CachyOS tweaks and setup guide for local AI agents, LLMs, and low-latency gaming.
Local AI Linux terminal assistant written in Bash. Explain commands, analyze files and logs, and use local LLMs or OpenAI-compatible APIs.
An entire internet — search, pages & links — hallucinated on the fly by the local Qwen-AgentWorld-35B-A3B world model. Sequel to jina-ai/node-serp.
Become a Tale Weaver! TaleWeaver is a free, open-source AI-powered visual novel creator. Build interactive stories, characters, scenes, sprites, backgrounds, and branching narratives using local AI tools like Llama and ComfyUI.
Self-host the modern LLM stack.
Patch set for llama.cpp — mmq_y=96, #pragma unroll, optimized for Pascal GPUs (SM 6.1)