Topic

Local AI models and the hardware to run them

The most common question we get is some version of "is my machine enough?" These posts answer it with numbers instead of vibes: VRAM tiers mapped to real GPUs, model recommendations per tier, and benchmark results for the open models that matter for coding.

Local models stopped being a compromise sometime in 2025. The current open-weight generation clears 70% on SWE-bench Verified at sizes a 16 to 24 GB GPU can run. The posts here track that frontier as it moves, model by model.

For live data instead of prose: the local LLM guide ranks 40+ models by coding benchmark and VRAM tier, and the VRAM calculator sizes a model to your exact hardware.

• April 3, 20267 min read

  Gemma 4: Google's first Apache 2.0 open model is also its best

  Google released Gemma 4 on April 2 under Apache 2.0. The 31B ranks #3 among open models globally and runs on a single RTX 4090.

• March 19, 20268 min read

  Are local LLMs good enough for coding in 2026?

  Are local LLMs good enough for real coding work in 2026? For most tasks, the honest answer is yes. Here is what actually changed.

• March 19, 20267 min read

  Which GPU for local AI? A developer's guide

  Which GPU do you need for local AI coding in 2026? The honest breakdown by VRAM tier, from 4 GB entry-level to 48 GB frontier.

• March 19, 20268 min read

  AI coding tools that work completely offline (2026)

  The complete list of AI coding tools that work with no internet. What they support, how they work, and what you give up going offline.

• March 19, 20267 min read

  How to run DeepSeek locally with Bodega One Code

  Run DeepSeek-R1 or DeepSeek-V3 locally with Bodega One Code. Which quantization to pick for your VRAM tier and how to set it up.

• March 19, 20266 min read

  LM Studio + Bodega One Code: complete setup guide

  LM Studio is the easiest way to run local models on Mac. Wire it to Bodega One Code in under 5 minutes. Which models to use and common fixes.

• March 3, 20268 min read

  Setting up Ollama with Bodega One Code: model guide

  Set up Ollama with Bodega One Code. The mistakes that cost people hours, which models the community uses, and how to wire it all together.

• March 29, 20266 min read

  How to use our free VRAM calculator for local LLMs

  Pick the right GPU for your local LLM setup. Our free VRAM calculator shows exactly how much memory each model needs, with quantization options.

More topics

Bodega One Code is the local-first AI IDE these guides are written around. Free for everyone in the open beta, commercial use included. Download free →