Posts tagged “open-source”

9 posts on SDAD Writes.

October 8, 2026

I Scored Every "Open Source" AI Model Released in 2026 Against the Actual Definition. None of Them Pass.

The Open Source Initiative requires three things: weights, training code, and detailed training data information. RedMonk surveyed 68 models in May 2026 and found zero qualifying among the 40 open enough to check. Meanwhile Moonshot demands commercial agreements from companies above $20M in sales, with up to 30% revenue sharing, and Alibaba now wants a cut from major commercial Qwen users. The label did not get abused. It got redefined into a revenue tier.

open-source llm deep-dive business

September 23, 2026

Laya vs Jev: The First Byte-Identical Benchmark of System One Decision Models

I ran the first head-to-head of the two open "System One" decision models, Laya and Jev, on 751 byte-identical inputs: same states, same questions, same seed, question hashes verified before comparing. Jev wins most suites for $0.008. Laya wins where it counts for a free model. A fourth column with Qwen 1.5B under constrained decoding completed the picture.

benchmark llm open-source local-ai

September 22, 2026

K2 Horizon: Six Fully Open Models and 21TB of Training Data

IFM released six foundation models from 0.9B to 375B, plus roughly 21.5TB of the actual training datasets, all Apache 2.0. I verified the dataset sizes and benchmarked the three small models myself: the 0.9B does real reasoning at 19 tokens per second in 2.2GB of VRAM. Here is what shipped, what is still missing, and where the catches are.

open-source llm deep-dive

September 19, 2026

Mojo and Vulkan - Running Local AI on Any GPU

Two developments are breaking NVIDIA's CUDA monopoly: the Vulkan compute backend for llama.cpp (cross-vendor LLM inference on any GPU) and the Mojo programming language (a CUDA alternative that compiles to any accelerator).

hardware local-ai open-source

September 18, 2026

Cloudflare Workers AI Free Models & OpenCode Integration Guide

Cloudflare Workers AI serves 50+ models from its edge network with 10,000 free Neurons a day. Since July 2026 the frontier coding models need the $5/mo Paid plan, but the free tier still covers real daily coding through OpenCode. What is free, what moved to Paid, and how I wire it up.

llm open-source ai-infrastructure

September 12, 2026

Heretic Complete Guide - Abliteration Philosophy Evaluation ARA MoE Models and Infrastructure

How Heretic removes refusal behavior from open-weight LLMs: my evaluation philosophy, Optuna TPE search learnings, the ARA next-generation ablation, why single constant vectors fail on MoE models, and what publishing 34 abliterated models taught me about attention-versus-MLP placement across Qwen and Gemma families.

llm open-source ai-agents

September 9, 2026

MiniCPM5 1B Small Model Landscape Swarm Control

Why about 1B parameters is the sweet spot for agent swarms: MiniCPM5-1B and six rival small models profiled from roughly 200 t/s on a $0.01/hr T4 down to 5 t/s on a Raspberry Pi 5, with the swarm economics at 1K, 100K, and 10M agents per day.

llm open-source ai-agents

August 31, 2026

RACER IS OP: How a Nobody With 8GB of RAM Decensored 38 Models on Free GPUs

No cluster, no budget, no PhD — just a MacBook Air with 8GB of RAM, a gaming PC, and every free GPU I could find. How I abliterated 38 models (97k+ downloads), rebranded the entire collection, and ended up decensoring models I trained myself.

llm open-source local-ai

August 30, 2026

We gave an AI agent a licence to act - and built the leash

SENTRY - an on-call incident responder that runs on TrueForge. It triages over MCP, correlates in a Daytona sandbox, and stops at a human Allow/Deny gate before any rollback. What TrueFoundry handled, what we wrote, and what broke along the way.

ai-agents open-source