WildEdge

Wild Edge monitors every inference, captures what degrades, and builds a dataset from real failures and user feedback. Automatically.

[WildEdge @getWildEdge]

Fine-tuning models starts with better datasets.

In this short demo, we show how https://t.co/HtPzNiNKqe helps you build fine-tuning datasets in 3 simple steps:

1. Filter interesting events
2. Build your dataset
3. Explore dataset analysis

Better data, better models.

[Google Gemma @googlegemma]

Want to teach Gemma to master chess?

Check out this awesome community project showing how to fine-tune Gemma 4 12B on your own data, 100% locally!

Running text, images, and audio on just 8GB VRAM makes custom models more accessible than ever.

[WildEdge @getWildEdge]

Does your app use AI?

Whether it relies
- on cloud API calls
- or runs fully offline on-device

WildeEdge lets you inspect every inference and workflow step.

Check out our short demo showing an app that turns speech into actions for an in-car assistant:

[Md Ismail Šojal 🕷️ @0x0SojalSec]

You can now fine-tune Qwen3.5

just need 5GB VRAM to train Qwen3.5-2B LoRA locally, 1.5x faster with 50% less VRAM.

Qwen3.5-4B Colab: - https://t.co/YYTtHQJ0eJ

- https://t.co/2wlamIRtZ6

[Gergely Orosz @GergelyOrosz]

Seeing how SOTA models are evolving: becoming more restrictive in usage (decided by the company), less transparent (you cannot tell if the AI lab nerfed your model) + less private (your prompts are stored, no opt out) makes me much more interested in open models + local inference

[Isalia20 @Is36E]

Apple just announced lower bit dtypes(FP8/FP4/2-bit Int) support coming to macOS 27 on WWDC!

https://t.co/BlApZf452b

[WildEdge @getWildEdge]

@BrendanFoody 🫡

[WildEdge @getWildEdge]

@muhammdrizwanmr @ultralytics Cool! Planning to release on GitHub?

[WildEdge @getWildEdge]

@himanshustwts 😋

[Victor M @victormustar]

Before the week ends, let's acknowledge one of the most INSANE week ever for open AI, with 25+ notable open-weight drops across every modality:

���� LLMs

→ NVIDIA Nemotron 3 Ultra: 550B hybrid Mamba-MoE, only 55B active, 1M context, MMLU 89.1. NVFP4 variant claims ~5x throughput on Blackwell. First openly-weighted 550B hybrid Mamba-Transformer, closing the gap with frontier closed models.

→ Google Gemma 4 12B: fully open dense any-to-any (text/image/audio/video), 256k context, encoder-free, 140+ languages, AIME 2026 at 77.5. Shipped with a 23-checkpoint QAT wave (mobile ONNX + MLX). Most deployable model of the week.

→ StepFun Step-3.7-Flash: 198B sparse MoE VLM, ~11B active, SWE-Bench PRO 56.3. Apache 2.0.

→ Liquid AI LFM2.5-8B-A1B: edge MoE, just 1.5B active, 128k ctx, MATH500 88.8, MLX-ready. Best on-device option this week.

→ JetBrains Mellum2-12B-A2.5B-Thinking: their first open MoE, near-Qwen3-14B coding at 2.5B active. Apache 2.0.

🎨 Image gen (the surprise of the week)

→ Ideogram 4: their FIRST-EVER open weights. 9.3B flow-matching DiT trained from scratch. #2 overall behind GPT Image 2, top open-weight model on Design Arena + LMArena. Strongest open checkpoint for text-rich images, full stop. It has taste. Still can't believe this is open weights.

🔊 Audio & Speech (a breakout week for open TTS, 4 labs shipped)

→ Boson Higgs Audio v3 4B: 102 languages, 21 emotions, singing/whispering/shouting, sub-second TTFA.
→ RedNote dots.tts: the only fully continuous (no codec) open TTS pipeline, Apache 2.0.
→ Google Magenta RealTime 2: real-time music gen, <200ms latency, text+audio+MIDI. multimodalart ported it to PyTorch within hours with live ZeroGPU demos.
→ NVIDIA Nemotron-3.5 ASR: 600M streaming, 17x more concurrent streams vs Parakeet RNNT 1.1B.

👁️ Vision & VLMs

→ PaddleOCR-VL-1.6: SOTA document parsing at 1B params, Apache 2.0.
→ Baidu NAVA: 6.3B joint audio-video gen, best-in-class A/V sync, Apache 2.0.

🎬 Video, 3D & World Models

→ NVIDIA Cosmos3-Super: 64B omnimodal world model coupling action trajectories with video+audio gen, for Physical AI.
→ JD JoyAI-Echo: up to 5-min multi-shot text-to-video on LTX-2.3.
→ ByteDance Bernini-R + VAST TripoSplat (single-image-to-3D Gaussian splats, MIT).

[WildEdge @getWildEdge]

@hthieblot Datasets

[WildEdge @getWildEdge]

@hthieblot Zero likes &gt; zero reach 🙃

[Google for Developers @googledevs]

Unlock local, agentic workflows with Gemma 4 12B and Google AI Edge, directly on your laptop. Experience 100% on-device AI:

• Generate code in AI Edge Gallery (new to Mac)
• Dictate and edit text via AI Edge Eloquent (new to Mac)
• Serve Gemma 4 12B locally with LiteRT-LM

Dive in: https://t.co/gr7tOrZmc0

[WildEdge @getWildEdge]

Most teams start with an LLM API. Then the bill shows up. Or latency breaks UX. Or accuracy problems your evals never caught.

Fine-tuning fixes those, but you need data you haven't been collecting.

WildEdge captures inference events as they run. Filter failures, build a dataset

[Ahmad @TheAhmadOsman]

LocalLLaMA Home Server Final Boss 😎