[mlx-code](https://josefalbers.github.io/mlx-code)
JosefAlbers
• NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Job Searcher
build-small-hackathon
• • 3Run Claude Code, OpenCode & Frontier Coding Models on Your Own AI Infrastructure with DEH
balaatdell
• • 1Nanochat-Ascend: Training Karpathy's Nanochat on Ascend NPU (Part 1)
leideng
• Announcing the Blackstone Graph
isaacus
• Thousand Token Wood: shipping a multi-agent economy on a 3B model
build-small-hackathon
• • 4RTX PRO 6000 Blackwell 96GB vs GH200: LLM Fine-Tuning Benchmark (Qwen3.5 SFT)
AlioLeuchtmann
• Training Data Vomit: How a 1.5M Character Payload Broke Gemini and Exposed the Triage Paradox
byte-vortex
• Fine-tune FLUX.2 [klein] with a LoRA under 60 minutes
black-forest-labs
• • 14From Operations to a Robot Arm
TheMuz
• • 2Fairness Pruning: Finding Demographic Bias Neurons in LLMs (And What Happens When You Remove Them)
oopere
• • 1How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent
nvidia
• • 37Task-Seeded Synthetic Q&A Generation for Nemotron Pretraining
nvidia
• • 12Build Small Hackathon With Cohere Models
CohereLabs
• • 1I Built a Surgical Tissue Segmentation Model — Here Is What I Learned
sugan04
• • 1Uncensoring Gemma 4 12B with Heretic — Keeping Vision, Audio, and the Encoder-Free Design Intact
junafinity
• TurboQuant in QVAC SDK 0.12.0: KV-cache quantization for production local AI
qvac
• • 2AutoResearch on Diffusers' Pipeline for 10 Rounds on JarvisLabs
chansung
• • 3int-llm: a pure-integer LLM experiment in C
nmicic
• 🔐 Sanitize a CSV of Customer Feedback with the ZeroGPU Router Plugin
its-maddy-a
• • 1