Reach 125K+ monthly visitors

Advertise on Trendshift

Local LLM

New 2026

Run Clark Air Sana 1.6B (ternary ~1.58-bit, GemLite INT2) natively under ComfyUI's KSampler

New 2026

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.

New 2026

Local-first, self-hosted home & records assistant: one LLM brain, scoped tools, durable memory. AGPL-3.0.

New 2026

Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.

New 2026

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

New 2026

BitNet 1.58 in MicroHs

New 2026

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.

New 2026

Brainstorm System design with an intelligent agent.

New 2026

yeah yeah it works on my machine

New 2026

CachyOS tweaks and setup guide for local AI agents, LLMs, and low-latency gaming.

New 2026

Local AI Linux terminal assistant written in Bash. Explain commands, analyze files and logs, and use local LLMs or OpenAI-compatible APIs.

New 2026

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.

New 2026

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.

New 2026

Self-host the modern LLM stack.

New 2026

Patch set for llama.cpp — mmq_y=96, #pragma unroll, optimized for Pascal GPUs (SM 6.1)