ANTIGRAVITY LABJP
TAG

local-llm

17 articles
Back to all tags
Related:
antigravity13lm-studio6gemma-46ollama5gemma45troubleshooting4multi-agent2latency1ai-tools1error1fix1proxy1
AI Tools/2026-06-24Advanced

When an Overnight Local Agent Crawls by Dawn — Keeping Ollama's Latency Flat by Working Backward from Context Length

Why each step of a long-running local agent gets heavier toward the end, how to measure it from Ollama's timing fields, and how a fixed num_ctx plus a rolling summary keep per-step latency flat.

AI Tools/2026-06-17Beginner

LM Studio Not Starting or Model Won't Load? Fixes for Mac & Windows (2026)

Fix LM Studio startup failures, model loading errors, and unresponsive local API server issues on Mac and Windows with step-by-step solutions and prevention tips.

Antigravity/2026-06-12Intermediate

Running Antigravity Behind a Proxy — Connection Design for Corporate Networks, SSL Inspection, and Hotel Wi-Fi

Keep Antigravity working behind corporate proxies, SSL inspection, and hotel Wi-Fi: layer-by-layer diagnosis, certificate trust, NO_PROXY design, and connection profiles with a local LLM fallback.

AI Tools/2026-06-12Advanced

Cutting Down 'Plausible but Wrong' RAG Answers — A Retrieval Evaluation Harness for Gemma 4 and Antigravity

Replace gut feeling with recall@5, MRR and faithfulness scores — a 30-question golden dataset and a small Python harness for evaluating a local Gemma 4 RAG stack.

Antigravity/2026-05-23Intermediate

Which Local-LLM Path to Keep with Antigravity: Ollama, LM Studio, or Raw Gemma 4 (Indie Judgment Notes)

After running three local-LLM paths from Antigravity in parallel, here is what I kept and what I cut, written from a one-Mac-mini indie operation.

AI Tools/2026-05-10Intermediate

Gemma 4 on Antigravity: Picking Q4 vs Q5 — What I Found After a Week on M2 Mac

A hands-on comparison of Gemma 4 quantization variants (Q4_K_M / Q5_K_M / Q8_0 / fp16) running locally with Antigravity on a 16GB M2 Mac, measured across speed, memory, and output quality.

Tips/2026-05-08Intermediate

How to Fix Out of Memory Errors When Using Gemma 4 in Antigravity

Getting out of memory errors when running Gemma 4 in Antigravity? This guide covers how to diagnose the issue and fix it—from switching to quantized models to tuning Ollama settings—based on real troubleshooting experience.

Antigravity/2026-05-06Intermediate

How to Fix LM Studio Response Cutoffs in Antigravity

When Antigravity cuts off LM Studio responses mid-stream, the culprit is usually one of four configuration issues. This guide walks through each cause and explains exactly how to fix it.

Agents/2026-04-24Advanced

Force Gemma 4 to Stay Inside Your Schema: A Production Guide to Constrained Decoding in Antigravity with GBNF, Outlines, and vLLM

A production-grade guide to running Gemma 4 locally in Antigravity while guaranteeing schema-compliant output. Covers llama.cpp GBNF grammars, Outlines with Pydantic, and vLLM guided_json — with concrete Python code and failure-mode fallbacks.

AI Tools/2026-04-24Intermediate

A Daily Workflow for Using LM Studio with Antigravity — Model Selection, Wiring, and Everyday Practice

A practical guide to making LM Studio your everyday model provider inside Antigravity — how to pick a model, wire up the OpenAI-compatible server, and survive the small surprises that come with daily use.

Antigravity/2026-04-24Intermediate

LM Studio Not Visible to Antigravity — Diagnosing Port, CORS, and Model-Load Layers

When Antigravity can't see LM Studio's models, the fix is rarely one setting. Walk through the three layers — server port, CORS, and model visibility — and recover cleanly, with the exact commands to verify each step.

Agents/2026-04-14Advanced

Antigravity × AgentKit 2.0 × Gemma 4: Cut API Costs by 80% with a Local Multi-Agent System in Production

A complete implementation guide to combining AgentKit 2.0 with locally-run Gemma 4, cutting cloud API costs by 80% while maintaining production-grade quality. Covers hybrid LLM routing, fault tolerance, and cost monitoring.