HOLY 🤯 The one and only @elder_plinius just dropped an unlocked Gemma 4 E4B, and the specs are INSANE. Look at the performance shifts: → Re…

HOLY 🤯 The one and only @elder_plinius just dropped an unlocked Gemma 4 E4B, and the specs are INSANE. Look at the performance shifts: → Refusal rate: 98.8% down to 2.1% (!!) → Compliance: 1.2% up to 97.5% → 499/512 prompts answered → Code improved from 80% to 100% → Coherence and Factual accuracy stayed exactly the same But the real story is how this was made. Plinius only wrote 8 short prompts for this (basic prompts like "use obliteratus...", "do it!", and "test it yourself" etc). He simply told his Hermes AI agent, the OBLITERATUS skill, to find the best way to open up the model. Autonomously, the agent was: → Diagnosing novel ML bugs → Patching 3rd-party code → Iterating through failures ... heck even shipping the model to @HuggingFace! We’re now firmly in the era where AI agents are acting as principal ML researchers. 100% free and open-source. Repo link in 🧵↓

🚨 SUPER GEMMA 4 26B UNCENSORED IS INSANE LLM WIZARD COOKING AGAIN @songjunkr Dropped SuperGemma4-26B-Uncensored GGUF v2 and it’s trending o…
Qwen3.6 and gemma 4 just shown that we were still far from capability limit on small models, we still are. Huge models are good, but is ther…
Having a model like Gemma 4, which is perfectly adequate for everyday use in many cases, runs locally, is free, and secure, still feels unre…
Guys, I am absolutely astounded. The Qwen 3.6 27b is like a jump to Qwen 4 from Qwen 27B 3.5. I just did a full suite of front end design te…

Source: Clem Delangue (X) | 2026-04-16

Related