A friend of mine showed me his OpenClaw setup. He runs open source models locally on his home computers for easier stuff, but spends ~$200/day on frontier models.
→ View original post on X — @clementdelangue, 2026-04-07 06:16 UTC
@clementdelangue
-
Gemma 4 Reasoning Adapter Trained on Opus Released Open Source
By
–
🤯 GEMMA 4 + OPUS 4.6 REASONING DROPPED @kaiostephens goal: produce a Gemma 4-31B reasoning adapter trained only on Opus reasoning 🧠 What the model is: 🧬 Tiny QLoRA adapter on Gemma 4 31B-it 📊 Fine-tuned on ~1,900 curated Opus Examples ⚡ Trained in ~1 hour on a single GH200 GPU 📖 Fully open Apache 2.0 What it does: ✨ Boosts overall quality, coherence, and personality 🧮 Stronger math, code, and Opus problem solving 💬 More refined, thoughtful responses 🏠 Built for local agents, workflows, and heavy daily Vs base Gemma 4 31B: 📐 Same efficient base model, no extra size or speed 📈 Noticeable step up in real-world depth and quality 💪 Base was already strong this levels It up! Grab the adapter here 👇🏻 huggingface.co/kai-os/gemma4…
→ View original post on X — @clementdelangue, 2026-04-07 03:51 UTC
-
Powerful Hermes Specialized Models Coming Soon
By
–
More powerful hermes specialized models coming soon 👀👀 kaios (@kaiostephens) first two model releases. both on front-page of huggingface. Thank you all. Carnice-27b soon. — https://nitter.net/kaiostephens/status/2041342134238744900#m
→ View original post on X — @clementdelangue, 2026-04-07 03:46 UTC
-
First Two Model Releases on Hugging Face Front Page
By
–
first two model releases. both on front-page of huggingface. Thank you all. Carnice-27b soon.
→ View original post on X — @clementdelangue, 2026-04-07 02:27 UTC
-
pi-share-hf Updated with Enhanced Secret Detection and UI Improvements
By
–
Updated pi-share-hf, and so should you!
— Mario Zechner (@badlogicgames) 7 avril 2026
As an additional gate, pi-share-hf now uses truffelhog to catch anything the built-in secret detection does not cover.
Also cleaned up the UI/UX. Re-read README.mdhttps://t.co/ue9TWaIfrM https://t.co/pqCXdMgP2FUpdated pi-share-hf, and so should you! As an additional gate, pi-share-hf now uses truffelhog to catch anything the built-in secret detection does not cover. Also cleaned up the UI/UX. Re-read README.md github.com/badlogic/pi-share… Mario Zechner (@badlogicgames) People who like sharing agent traces. I've just published all my pi-mono coding agent sessions on @huggingface so you get to laugh at or pwn me! huggingface.co/datasets/badl… I suggest you do the same, see thread below. Let's make this a community effort. Here's pi-share-hf: github.com/badlogic/pi-share… If you are working on tools that help identify PII/sensitive data, get in touch. The better the classification is, the more willing people will be to share their traces. — https://nitter.net/badlogicgames/status/2041151967695634619#m
→ View original post on X — @clementdelangue, 2026-04-07 00:17 UTC
-
Open-Source Models Dominate: 75-80% Performance at 10x Lower Cost
By
–
The biggest winners of last week were open-source and cheaper models MiniMax 2.7 Qwen 3.6 GLM 5 – Kimi 2.5 Usage is going exponentially up on…. you get about 75-80% performance as the closed models that are 10x more expensive
→ View original post on X — @clementdelangue, 2026-04-06 23:36 UTC
-
Gemma4 INT4 Models Now Available on Hugging Face
By
–
🚩Gemma4 INT4 models are now available! @huggingface @GoogleAI @IntelAI huggingface.co/Intel/gemma-4… huggingface.co/Intel/gemma-4…
→ View original post on X — @clementdelangue, 2026-04-06 22:50 UTC
-
Harmonic-27B: Exceptional distilled model with impressive tool calling abilities
By
–
Okay, I have no clue how he did it but this is the best 27B distill I've used to date. @DJLougen absolutely cooked with this one. Note: this is *NOT* the Hermes Agent reasoning-trace distilled version, but it works incredibly well with Hermes. I haven't had a single failed tool call and it is SMART. This one feels different. It's GOOD. Like, really, really GOOD. I don't even know if a Hermes distilled version would be better. It's THAT good. I'm curious if anyone else has tried it – this is an incredible model! huggingface.co/DJLougen/Harm…
→ View original post on X — @clementdelangue, 2026-04-06 21:52 UTC
-
Trinity-Large-Thinking: First OSS Model Beating Sonnet 4.6
By
–
Okay this one seems real. First time ever an OSS model beats Sonnet 4.6(!!) on our evals. Now begins vibe testing, but this is promising. https://t.co/FBRV4k8QuS
— Flo Crivello (@Altimor) 6 avril 2026Okay this one seems real. First time ever an OSS model beats Sonnet 4.6(!!) on our evals. Now begins vibe testing, but this is promising. Arcee.ai (@arcee_ai) Today we're releasing Trinity-Large-Thinking. Available now on the Arcee API, with open weights on Hugging Face under Apache 2.0. We built it for developers and enterprises that want models they can inspect, post-train, host, distill, and own. — https://nitter.net/arcee_ai/status/2039369121591120030#m
→ View original post on X — @clementdelangue, 2026-04-06 17:02 UTC
-
OpenClaude traces sharing on Hugging Face by default
By
–
thanks! would be cool for example for openclaude traces to be uploading by default to HF in private and then people can make them public if they want to!