Jovan Chan - DEV Community

Jovan Chan

Jun 12

Mac Studio M4 Max vs Mac Mini M4 Pro for Local AI in 2026: Is the $600 Upgrade to 546 GB/s Worth It?

#macstudio #macmini #m4max #m4pro

6 min read

Jovan Chan

Jun 12

Kimi K2.6 for Local AI in 2026: What VRAM and System RAM You Need to Actually Run the 1T-Parameter MoE Coding Leader

#kimik2 #localllm #moe #hardwareguide

6 min read

Jovan Chan

Jun 12

RTX 4080 Super 16GB for Local AI in 2026: 736 GB/s on the Used Market, and Why the Math Is Tighter Than You'd Think

#gpu #rtx4080super #localai #localllm

6 min read

Jovan Chan

Jun 12

LibreChat Setup Guide 2026: Plugins, Agents, and Ollama

#librechat #ollama #selfhosted #docker

5 min read

Jovan Chan

Jun 12

Kimi K2.6 Setup Guide: MIT-Licensed 1T Coding Model

#kimi #llm #selfhosted #coding

5 min read

Jovan Chan

Jun 12

Open-Source Coding Agents 2026: Which One to Run

#aider #cline #openhands #codingagents

5 min read

Jovan Chan

Jun 12

Cline + LM Studio 2026: complete setup guide, the 32k context trap, and which coding models actually hold up

#cline #lmstudio #localllm #setupguide

5 min read

Jovan Chan

Jun 12

Claude Code agentic API rate limits in June 2026: what the new credit separation means for solo devs and teams, and how to optimize your usage cap

#claudecode #ratelimits #agentic #pricing

5 min read

Jovan Chan

Jun 12

Aider + LM Studio 2026: setup guide, the output-token ceiling that truncates diffs, and which models actually hold up

#aider #lmstudio #localllm #setupguide

5 min read

Jovan Chan

Jun 11

Qwen 3.7-Max for Local AI in 2026: What VRAM You'll Need When the Open Weights Drop

#qwen #localllm #vram #moe

6 min read

Jovan Chan

Jun 11

Qwen 3.6 35B-A3B for Local AI in 2026: The 24GB VRAM Line That Gets You 120 tok/s

#qwen #localllm #gpu #vram

6 min read

Jovan Chan

Jun 11

NVIDIA Rubin CPX for Local AI Inference in 2026: What the New Context-Optimized Blackwell GPU Means for Home Labs vs Consumer Cards

#nvidia #gpu #localai #inference

5 min read

Jovan Chan

Jun 11

Open Interpreter vs Aider vs Claude Code Local 2026

#aider #openinterpreter #codingagents #ollama

5 min read

Jovan Chan

Jun 11

Ollama Security 2026: Lock Down Your Exposed LLM Server

#ollama #security #selfhosted #linux

5 min read

Jovan Chan

Jun 11

Ollama + Open WebUI + pgvector: Sovereign RAG Stack 2026

#ollama #openwebui #pgvector #rag

5 min read

Jovan Chan

Jun 11

Cursor Teams June 2026 pricing: Standard $32/seat vs Premium $96/seat — what 5 the usage limit actually buys

#cursor #pricing #teams #comparison

5 min read

Jovan Chan

Jun 11

Cursor + Ollama and LM Studio in 2026: use local models for Chat and Cmd+K — and keep tab completion honest

#cursor #ollama #lmstudio #localllm

5 min read

Jovan Chan

Jun 11

Continue.dev + Ollama 2026: local AI coding setup for VS Code and JetBrains with no API key

#continuedev #ollama #localllm #setupguide

5 min read

Jovan Chan

Jun 10

Nemotron-Cascade 2 for Local AI in 2026: 187 tok/s on RTX 3090 and What 30B Total / 3B Active Really Means for Your GPU

#nvidia #nemotron #localllm #gpu

6 min read

Jovan Chan

Jun 10

ComfyUI NVFP4 in 2026: 3 Faster Image Generation on RTX 50-Series (and the Right Format for RTX 40-Series)

#comfyui #nvfp4 #flux #imagegeneration

6 min read

Jovan Chan

Jun 10

DDR5 and SSD Prices Doubled in 2026: How AI's HBM Shortage Is Wrecking Home Lab Build Budgets (and What to Buy Now)

#ddr5 #ssd #memory #localai

6 min read

Jovan Chan

Jun 10

Open WebUI Pipelines Guide 2026: Web Search, Rate Limiting, and Custom Logic for Your Local LLM

#openwebui #ollama #selfhosted #ai

5 min read

Jovan Chan

Jun 10

Open-Source LLM License Guide 2026: MIT, Apache, GPL, Llama

#licensing #llm #opensource #legal

5 min read

Jovan Chan

Jun 10

Tabby Team Server Setup 2026: Self-Host Code Completion

#tabby #selfhosted #coding #docker

5 min read

Jovan Chan

Jun 10

Continue.dev + LM Studio 2026: setup guide, the context-window dial you must set before loading, and which GGUF models pass the FIM test

#continuedev #lmstudio #localllm #setupguide

5 min read

Jovan Chan

Jun 10

Windsurf Is Now Devin Desktop: What the June 2 Rebrand, Agent Command Center Default Surface, and Open ACP Protocol Mean for Your AI Coding Stack

#windsurf #devin #acp #aicoding

5 min read

Jovan Chan

Jun 10

Kimi K2.6 in Cursor and Cline in 2026: free-tier setup via OpenRouter, the temperature fix, and when to drop GPT-5.5

#kimi #cursor #cline #openrouter

6 min read

Jovan Chan

Jun 9

The Highest-Leverage File in an AI-Assisted Repo Is Your CLAUDE.md (or AGENTS.md)

#ai #claude #cursor #productivity

2 min read

Jovan Chan

Jun 9

GPT-OSS 20B for local AI in 2026: 225 tok/s on RTX 4090, the 128k context trap, and which GPU you actually need

#gpu #localllm #ollama #openai

6 min read

Jovan Chan

Jun 9

GLM-5.1 Review 2026: MIT 744B MoE That Tops SWE-Bench Pro

#glm #llm #coding #localllm

5 min read

Jovan Chan

Jun 9

Devstral Small 2 Review 2026: 68% SWE-bench on RTX 4090

#devstral #mistral #localllm #coding

5 min read

Jovan Chan

Jun 9

CodeGraph Setup Guide 2026: Cut Claude Code Tool Calls by 58%

#claudecode #cursor #mcp #codegraph

1

5 min read

Jovan Chan

Jun 9

OpenHands 1.7.0 + Ollama in 2026: complete local setup, the Docker networking trap, and which models actually complete agentic tasks

#openhands #ollama #localllm #setupguide

5 min read

Jovan Chan

Jun 9

Gemini 3.5 Flash as your Cursor and Cline backend in 2026: $1.50/M tokens, 76.2% on Terminal-Bench, and how it stacks up against Claude Sonnet

#gemini #cursor #cline #setupguide

6 min read

Jovan Chan

Jun 9

Cursor tab completion not working in 2026: 8 fixes ranked by how often they actually work

#cursor #troubleshooting #fix #autocomplete

1

5 min read

Jovan Chan

Jun 8

Framework Desktop AMD 395+ (rdna 3.5) cannot run confyui err Fix 2026

#fix #tutorial #ai #troubleshooting

2 min read

Jovan Chan

Jun 8

RuntimeError: shape [1, 68, 120, 16, 2, 2] is invalid for Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 8

orch.AcceleratorError: Chyba CUDA: Fix 2026

#fix #tutorial #ai #troubleshooting

2 min read

Jovan Chan

Jun 8

Self-Hosted AI for Dev Teams 2026: No Subscriptions

#tabby #librechat #anythingllm #selfhosted

5 min read

Jovan Chan

Jun 8

pgvector vs Chroma vs Qdrant for Local RAG 2026

#rag #vectordatabase #pgvector #chroma

5 min read

Jovan Chan

Jun 8

vLLM Production Setup 2026: Nginx, Auth, Multiple Models

#vllm #ai #llm #docker

4 min read

Jovan Chan

Jun 8

DeepSeek V4-Flash as your Cursor and Cline backend in 2026: $0.14/M tokens, MIT license, and when it actually beats Claude Sonnet

#deepseek #cursor #cline #localllm

5 min read

Jovan Chan

Jun 8

Zed parallel agents vs Cursor agent mode in June 2026: should you switch your $20/month to the faster native editor?

#zed #cursor #localllm #vs

5 min read

Jovan Chan

Jun 8

Agentic Coding Starter Kit Review 2026: Is $9 Worth It for Claude Code and Cursor Users?

#claudecode #cursor #review #tools

5 min read

Jovan Chan

Jun 7

Regression: large GGUF models work on Ollama 0.24 but fail o Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 7

ollama launch codex-app sets wire_api=responses for local Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 7

macOS 0.30.6: /api/embed with qwen3-embedding:0.6b crashes l Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 6

Bug: `ollama create --experimental` writes 0/blank metadata Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 6

500 Internal Server Error: llama-server process has terminat Fix 2026

#fix #tutorial #ai #troubleshooting

2 min read

Jovan Chan

Jun 6

Request for help: qwen2.5vl:32b fails to load CLIP model aft Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 6

[BUG] Aider ignores model setting when generating commit mes Fix 2026

#fix #tutorial #ai #troubleshooting

2 min read

Jovan Chan

Jun 5

Too many open-source tools, never findable: a curated index for AI video, downloading, scraping & automation

#opensource #ai #productivity #webdev

2 min read

Jovan Chan

Jun 5

RuntimeError: Given normalized_shape=[2560], expected input Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 5

hostbuf_file_reader_read failed Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 5

Assets IMPORT not visible BUG Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 5

Uncaught FileNotFoundError in <frozen posixpath> line 412 Fix 2026

#fix #tutorial #ai #troubleshooting

2 min read

Jovan Chan

Jun 5

Uncaught AttributeError in init.py line 1729 Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 5

Safety Report: AI Guardrails Do Not Work — 56-Day Proof (06K Fix 2026

#fix #tutorial #ai #troubleshooting

1 min read

Jovan Chan

Jun 5

Stop Paying Per Image: Run Image Generation Locally on a GPU You Already Own

#ai #machinelearning #productivity #opensource

2 min read

Jovan Chan

Jun 5

[Bug]: 500 Internal Server Error in v0.30.4 due to non-ASCII Fix 2026

#fix #tutorial #ai #troubleshooting

2 min read

Writing Debut