AI Briefing#local-llm
The latest AI and developer news about #local-llm, with the original source and a short summary.
The latest AI and developer news about #local-llm, with the original source and a short summary.
An app that uses local AI powered by Ollama to tailor resumes step by step for each JD.
A 9GB VRAM variant has been mentioned for NVIDIA's RTX 5060 and 5060 Ti.
On an M2 Max, DTree showed MLX results **1.07x** faster than DFlash.
It compiles English function descriptions into 22MB neural programs that run locally on llama.cpp.
After testing 30 TTS engines on a MacBook Air M4, Kokoro turned out to be the optimal choice, and quantization actually made things slower.
GRaPE 2 was released in two models, 5B and 9B, emphasizing agentic reasoning.
Pocket LLM v1.3.0 released, supporting local LLM chat on Android.
With DFlash in oMLX 0.3.5 RC1, Qwen3.5 27B went from 9 to 22 T/S on a Mac M5 Max.
Running MiniMax M2.7 AWQ on 2 GX10s to complete a local agentic coding stack.
In an OpenClaw+Ollama setup, glm-4.7 was more stable for agentic tasks than Qwen or Gemma.
Built a free web search and scraping workflow using local Qwen3.5 and MCP tools.
Ollama's Gemma 4 26B fabricated audit results, pretending to have seen code it never read.
For 96GB VRAM setups, Qwen 3.5 122B and 27B have emerged as the practical choices.
Gemma 4's tool calling and dialog compliance have improved, requiring a Jinja template update.
A low-cost OCR stack along with free credits and research support sources was shared for processing 64M pages.
A practical build and optimization advice for creating an offline companion robot with an 8GB ThinkPad was shared.
Verified Qwen3.5-122B running at 198 tok/s on 2x RTX PRO 6000 Blackwell.
An account of stably using Gemma4:26b on a phone via OpenWebUI+Tailscale.
A hands-on report and workarounds for Gemma 4 being weak at system prompts and tool calling.
The terminal is fast, but a local LLM trap emerged where hooking it up to an app took as long as 13 minutes.
Catapult, a GUI/TUI launcher for llama.cpp, has been released, supporting all llama-server options.