Introducing OUI-1: the first open-weights model for Generative UI... 71.7% on Generative UI Bench at 4B params. Beats Gemma 4 31B with 8× fewer active params, and scores 5.5× the base DiffusionGemma it was fine-tuned from. Methodology, weights, and full benchmark results in the blog 👇show more

how small can you make a world model? we... built mira mini, the first reproduction of mira: •⁠ ⁠reproduced in a week from scratch •⁠ ⁠four players, one shared rocket league match, in the browser •⁠ ⁠distilled to 364m params, weights, code, full report: all open. play it here ↓show more

Introducing Jan v3, with updates to Jan Desktop v0.7.6... 💛 Jan v3 is our first v3 model, a 4B base built for fine-tuning and fast local use, with stronger math and coding. This release also includes a small Jan Desktop update, starting with a UI refresh as we move toward a more unified Jan experience. Try it: - Jan v3 is available in Jan Desktop and at - Get the latest desktop app at Model: - Jan-v3-4B: - Jan-v3-4B-GGUF: Thanks Qwen for the base model and Georgi Gerganov for llama.cpp 💛show more

Bonsai 27B running locally on an iPhone in Atomic... Chat! Bonsai is the first 27B-class model that fits on a phone. PrismML built it on Qwen3.6 27B with 1-bit weights. It takes 3.9GB instead of 54GB and keeps ~90% of the benchmark scores. Available now on iPhone and Androidshow more

world models have their comfyui now. introducing alakazam studio,... the first local, open source UI for world models. •⁠ ⁠sentence goes in => you edit the state graph => play •⁠ ⁠on a live model, yours, running in your browser •⁠ ⁠⁠apache-2.0, fully open source fork it and point it at your model 👇show more

Introducing Nomic Embed - the first fully open long... context text embedder to beat OpenAI - Open source, open weights, open data - Beats OpenAI text-embeding-3-small and Ada on short and long context benchmarks - Day 1 integrations with @langchain, Llama-index, MongoDBshow more

1/ Introducing Glider - the smallest model to beat... GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥show more

Tiny Recursive Models: A tiny 7M parameter model that... recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍show more

Meet Mistral Large 4, aka Le Chonk. • 1T... parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding. • Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure. • Available to all via API today. Working with cybersecurity partners privately. Open weights release end of October.show more

I've started using Base UI for Hypermode's new UI... components and I'm absolutely loving it. The component API's are excellent, and the DX in pairing it up with Motion has been seamless. WIP of a new Hypermode dialog with form elements built on BaseUI 👇show more

Open weights just caught up to the frontier. GLM-5.2... from Z.ai tops the open-model rankings on Artificial Analysis and Arena.ai's Agent Arena. It's now live on CoreWeave Serverless Inference at $1.39 in and $4.40 out per 1M tokens. Ship more for less.show more

the 24gb vram tier is enough for most builder... work in 2026. gemma 4 31b dense on my rog scar 18 just autonomously built a production hero section in one prompt, one html file and 5 minutes end to end. hardware: rog scar 18, rtx 5090 laptop 24gb vram. model: google gemma 4 31b dense at q4_k_m quant, using 22.8 of 24gb. engine: llama.cpp built for blackwell (sm_120). harness: hermes agent with native tool parsing. speed: 15 tok/s sustained, 94 watts, 50c. flags i used: ./build/bin/llama-server -m ~/models/gemma4-31b/google_gemma-4-31B-it-Q4_K_M.gguf -ngl 99 -c 131072 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 --jinja --host 127.0.0.1 --port 8080 if you own 24gb vram in 2026, you have enough for most ui work, most agentic coding, most autonomous builds. no subscription, no one logging your prompts. a dense open model on consumer hardware shipping real software on your desk. this was the warmup. full page next on same hardware, then the octopus invaders final multifile autonomous challenge.show more

Introducing FLUX.2 [klein]. Blazing fast. Beautiful. Generate stunning images... in under a second while maintaining exceptional quality. Great for fast editing, changing styles, and developing ideas from 0 → 1. Available via API, or run it locally - Klein 4B under Apache 2.0, Klein 9B as open weights. Try it for free in our demo app (link in the thread).show more

We built a better alternative to json-render & A2UI... Up to 3x faster rendering & 67% fewer tokens. Far fewer broken outputs. We've been shipping Generative UI interfaces to 10,000+ developers for the past year. We know where JSON-based rendering breaks in production. So we built a new format - one that works with how models actually generate, not against it. And today we're open sourcing it: openui [dot] comshow more

/1 Gemma 4 31B just crushed Qwen 3.6 27B... in a local LLM gamedev contest inside atomic.chat (prompt is below) Device: MacBook Pro M5 Max, 64GB RAM Results: Qwen 3.6 27B: 32 tokens/sec · 18m 04s · 33,946 tokens Gemma 4 31B: 27 tokens/sec · 3m 51s · 6,209 tokens So what is more important: tokens per second, or the quality of the final answer? Qwen made a very long response and showed more creativity and visual style. But Gemma gave a shorter, clearer, and more logical answer in much less time. In this one-shot Pac-Man gamedev contest, Gemma 4 31B was the clear winner. Its game logic was stronger: click reactions were smoother, and it handled interactions with elements like walls, ghosts, and particle effects better. But this was only one test. Maybe Qwen 3.6 27B can show better results with better settings. Open the comments, try our prompt, and share your result below.show more

my 8 GB VRAM gaming laptop is absolutely going... to hate me for this. but I still did it. ran a 31b dense model (Gemma 4 31b Q4) with only 8 GB VRAM last week I ran Gemma 4 26B A4B a mixture of experts model on my RTX 4060 and hit 25–28 tokens/sec using llama.cpp's new MTP support. smooth. snappy. but MoE has a secret: it only activates 4B parameters per token despite having 26B total. that's why it flies. so the real question started haunting me. what if I throw a full, no tricks, every parameter fires on every token, 31B DENSE model at the same machine? # Hardware: GPU: NVIDIA RTX 4060, 8 GB VRAM RAM: 16 GB CPU: Intel Core i7 H Laptop. Gaming. Modest. The model: gemma-4-31B-it-qat-UD-Q4_K_XL.gguf (model's unsloth huggingface link in the comments) This is Google DeepMind's flagship dense model in the Gemma 4 family that can run on single consumer GPU. It packs a hybrid attention architecture, supports up to 256K context natively, and is QAT (Quantization Aware Training) optimized, meaning it retains far more quality than standard post training quants at the same bit depth. This is NOT the MoE. This is 31 BILLION dense parameters, every single one of them loaded. # the flags I used: -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -cnv --spec-type draft-mtp --spec-draft-model mtp-gemma-4-31B-it.gguf --spec-draft-n-max 8 --spec-draft-p-min 0.6 -c 6000 -v Multi Token Prediction (MTP) is still active here. Separate draft GGUF required, same as the 26B setup. # Results: → Decode: ~3 tokens/sec → Prefill: ~2 tokens/sec → Context: 6000 tokens → Hardware crying quietly in the corner: yes so is 3 tps actually usable? For real time back and forth chat? Not ideal. You're not having a fluid conversation at 3 tps. but slow ≠ useless. And this is where it gets genuinely interesting. think about how senior devs actually work in a real team. But when something is architectural, deeply complex, or needs serious reasoning? they walk down the hall and escalate to the senior. That's exactly the local AI agent architecture this unlocks: → Fast orchestrator model (Gemma 4 26B MoE at 25+ tps) handles routing, simple queries, tool calls, memory. The junior dev. → Gemma 4 31B dense is the senior, called only when the fast model genuinely hits a wall. Hard multi step reasoning. Complex code generation. Deep architectural decisions. The agentic loop stays fast. Only the hard hops touch the 31B. That's a legitimate production grade local AI architecture on a budget hardware. (requires 2 8gb gpus) other workflows where 3 tps is completely fine: - overnight batch jobs. summarize documents, extract structured data, review code. Fire it off. Sleep. wake up to results. - One shot deep reasoning - Silent code audit loops, you write and test, the 31B reviews diffs and flags issues in the background between your sprints - Any workflow where output quality > output speed A few weeks ago, nobody was running a 30B+ dense model on a single consumer GPU with 8 GB VRAM. At all. Now we're doing it on an Intel i7-H gaming laptop with a NVIDIA RTX 4060, thanks to llama.cpp + QAT quants + MTP speculative drafting. Google DeepMind said the Gemma 4 31B targets "consumer GPUs and workstations." They were not exaggerating. The hardware bar to run serious frontier class models locally keeps dropping. the tools are here. the models are here. you just have to be willing to abuse your laptop a little. what workflows would you actually run on a local 3 tps 31B dense model? genuinely curious. drop it below.show more

Big win for open-source LLMs! DeepSeek V4 Pro holds... the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.show more

> be Muse Spark Open > Meta's Llama 4... disappoints everyone > Meta goes closed with Muse Spark > Zuck writes a $100-200 billion check > Muse Wonder ships on Monday > 3 days later Meta drops you with open weights > 816 billion parameters > only 42 billion active at a time > 1 million token context > built for coding and long agent tasks > runs on two Mac Studios on a desk > Meta calls you the most capable US open-weight model ever > every Chinese lab reading the model card America is back in the open-weight game.show more

One UI 8 Newer Version of Weather App Fixed... lag on all devices when the weather is Sunny and changed the position of the sun so it doesn't overlap with text. 1 and 2: Older Version from @choehau_alen 3 and 4: Newer Versionshow more

I just ran Gemma 4 31B on @CerebrasSystems at... 1,800+ tokens/sec and it's multimodal. For context: that's 35x faster than a typical GPU endpoint, and the first token (reasoning included) lands in 1.5 seconds. This isn't a benchmark slide, I recorded the inference live. Prompt I used: "Create a simulation of an iPhone. Include at least one working dummy note taking app, a functional notification pulldown, high quality graphics, single HTML file, any libs via CDN." - Generation time: 3 seconds. - Notes app worked. - Notification panel worked. - Rendered first try. This is what wafer-scale inference unlocks, not just "faster," but a different category of product. When generation is this fast, you stop waiting and start iterating in real time. Why this matters: Gemma 4 31B is Google DeepMind's flagship open weight model, Apache 2.0 licensed, dense (not MoE), and built for efficiency over raw parameter count. It scores close to Claude Haiku 4.5 on the Artificial Analysis Intelligence Index (30 vs 29) but runs ~18x faster on Cerebras. It's also the first multimodal model on Cerebras's platform, meaning you can now feed it screenshots, documents, charts, and UI states at wafer scale speed. # Applications I'm most excited about: - Screenshot → Insight: Drop in a dashboard or document screenshot, get structured findings back instantly. no waiting, no batching. - Live UI generation: Full interactive interfaces (like my iPhone sim) generated and rendered in under 2 seconds. - Screenshot -> Patch: Feed it a broken UI + console error, get a minimal code fix and verification steps back. - Computer use & agentic loops: See -> reason -> act - verify, fast enough to keep a human in the loop instead of waiting on the model. - Long context summarization: Full research reports condensed into decision ready summaries you can read and requery in one sitting. The bigger unlock isn't the speed number itself, it's that agentic and multimodal loops (see -> reason -> output -> tool call -> verify -> retry) finally run in real time instead of feeling sluggish. As Logan Kilpatrick (Logan Kilpatrick) put it: "If every model was doing 2,000 tokens per second, you wouldn't build the same product and just have it be faster, you'd build different products." Gemma 4 31B is live now on Cerebras Inference Cloud in public preview. If you're building multimodal, agentic, or real time apps, this is worth testing today. What would you build with such insane inference throughput?show more

Full player UI with audio, CRT shader and SFX... on #unity + #aseprite for sprite work. It works similar to the pipboy in fallout, basically one-in-all tablet like console the player always carry. Can u guess what the game play would be like from the UI. #gamedev #indieshow more