Our Blog

Fourteen Apache-2.0 and MIT open-weight models that fit one TPU v5e chip, served one after another through vLLM on the same pinned image and scored on GSM8K and BFCL against Gemma 4 E2B. Qwen3-4B matches Gemma's accuracy at 0.57x its output, SmolLM3-3B and Granite 3.3 2B match it on tool calls, and Gemma keeps the lead on long prompts.

Every "7 local models that replace Claude Code" list opens the same way: a table of SWE-bench scores,...

One right answer is not the same as a good sequence of decisions. eSlams is building a public stadium...

You’ve read way too many versions of this paragraph already. Probably even this week: “In today’s...

What I Built SoloDesk AI is a privacy-first, zero-marginal-cost financial copilot and invoice...

Beyond chat with llamadart · Part 2 Llama Village, where five llamas share a world without sharing...

Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for...

Let me ask you something. What are you supposed to learn when the CEOs of all AI companies keep...

A few months ago, I published You're a Real JavaScript Developer Only If... It was supposed to be a...