Only Opensource model can DO ！ WAN animate with... SDPOSE Running on 8G VRAM and 32G RAMshow more

Only Opensource video model can do!

Generate Long Videos with Wan even on Low VRAM... machines! [NVIDIA ONLY] With this super-optimized gradio app from deepbeepmeep you can generate up to 12 second videos with Wan. And even generate on low VRAM machines! - Generate up to 12 sec videos - Run on 5GB~ VRAM (Read the full thread)show more

INSANE...this is an Open Source Video model available for... free on Hugging Face. LongCat just dropped an amazing video avatar model that can do crazy things. And it's 100% Opensource.show more

With Wan2.1-FLF2V-14B, videos are instantly and effortlessly transformed into... brighter, more vibrant styles! 🌈 #AlibabaAI #Innovation #Wan #OpenSourceshow more

Coming soon: WAN 2.2-S2V — our cinematic speech-to-video model.... Driven by audio. Built on vision. Open source. Let every voice find its vision. #AIGC #VideoGeneration #OpenSource #SpeechToVideoshow more

FPS in top left corner 40fps realtime with video... & 4.6gb VRAM ✅ 50fps realtime with image & 1.7gb VRAM ✅ Running locally on a 4090 o3mini w/ Cursor go brrrrrrrrrrrrrrrrrrrrrrrrrrrrrrshow more

Wan-Animate officially open-sourced the release weight! I had the... chance to test this model early yesterday, and it's working great! Even complex dances can be perfectly replicated，And it retains the character features without any obvious blurriness.show more

Today I am releasing my FlipDot Controller App. Coded... in Processing you can easily draw and animate on these amazing displays. If you don't have any FlipDot panels you can still use this App as a simulator. #flipdots #opensourceshow more

Running Linux on a computer with 32GB RAM be like:

Holy shit... it's over. Wan 2.2 Animate with Nano... Banana can replace any actor in any film with just one click. FREE tutorial + Nano Banana prompt👇show more

So right now basically anyone with a 16GB VRAM... card can go on Hugging Face and download a model which BEATS Claude Sonnet 4.5, all running locally 🤯 LOOK AT THE WATER PARTICLES?? What are they doing in these labs man What is this Unsloth AI UD quantization magic?? I'm running the lowest Q3 here, it oneshots everything 😭 Bros what is happening?show more

Run Gemma 4 26B MoE on 8GB VRAM with... 250k context at 20+ tokens/sec If you own any 8GB VRAM graphics card, stop what you are doing. Local AI just had its absolute "Holy Shit" moment for budget hardware. Yesterday, I benchmarked Unsloth Gemma 4 12B Q4_K_XL on an 8GB card. The community went wild but immediately demanded more: "Can we run a 25B+ model on budget GPUs?" Today, I’m delivering exactly that. I am running a massive 26B parameter Mixture of Experts (MoE) model locally on a standard 8GB VRAM setup with 250k full native context!. If you own an RTX 3060, 3070, 4060, or any budget GPU with 8GB of VRAM, the local AI paradigm has completely changed. The performance metrics are astonishing: - 20 tokens/sec flat decode throughput. - Stable, flat decode speed even with massive prompts. - I threw a 60k token prompt at it, and it still clocked in at 20 TPS without dropping a single frame. # What about prefill? Yes, Time To First Token (TTFT) is slightly high when swallowing massive contexts. But with a solid 200 tokens/sec prefill speed, the wait is barely noticeable and highly usable. And this is running completely without Multi Token Prediction (MTP) active. How is this possible? It’s the magic of Google's new QAT (Quantization Aware Training) quants for Gemma 4. The model weight file (unsloth gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf) is only 13.2 GB, making it the ultimate local powerhouse. # The Test Setup: CPU: Intel Core i7 RAM: 16GB System RAM GPU: NVIDIA GeForce RTX 4060 Laptop GPU (8GB VRAM) # The Secret Sauce (The -cmoe Flag) To make this work properly on any 8GB card, you must use the -cmoe (CPU MoE) flag in llama.cpp. This flag isolates the heavy MoE expert weights directly to system memory (CPU/RAM) while letting your GPU focus strictly on the Attention layers and the KV Cache. It prevents VRAM spillage and holds the throughput rock solid. # The flags: -m "gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf" -cmoe -c 248000 -v Once running, just open the UI on localhost and toggle the new reasoning lightbulb icon in the text input box to watch the model perform multi step thinking. Are you still running smaller models, or are you ready to scale up your budget local setups? Let's discuss in the repliesshow more

Free Blender AI Motion Capture Plugin: Runs a 1-billion-parameter... model on a GPU with 8GB VRAM, supporting real-time capture and video uploads — no cost required.show more

Introducing DeepThought-8B: Transparent reasoning model built on LLaMA-3.1 with... test-time compute scaling. - JSON-structured thought chains & controllable inference paths. - ~16GB VRAM, competitive w/ 70B models. - Open model weights, and inference scripts.show more

Honestly impressed by how far Kling AI has come.... Side-by-side with Runway and WAN 2.2 Animate, Kling AI clearly leaves them in the dust 🤯 You can try the new Kling AI here: →show more

GPT-4o level multimodal LLM running on your phone. MiniCPM-V... 4.5 outperforms GPT-4o, Gemini-2.0 Pro, and Qwen2.5-VL 72B on vision and language AI tasks. It can even understand videos and perform OCR in 30+ languages. And it's 100% Opensource.show more

gta 5 ps3 with only 512mb of ram and... has ferris wheel reflections meanwhile gta 6 which is running on modern hardware and the biggest budget of all time can't mange and yet these drones on here ready to preorder thursday lmaoshow more

I saw a tiktok meme and had a stupid... idea to redo a version of it with Ember Can someone who can animate it better do this please its a good idea wasted on a low animator XD Ember Heirloom model by: SumSmutCreator 🔞 || Commissions Open! Spare a coin to my ko-fi?show more

Qwen has just released a model on par with... GPT-4o... And you can run it locally easily 🤯 Yep. GPT-4o level AI running offline on a laptop. - Fully open source - Only 3B active parameters - 262k context length natively Quick steps to run it on your machine and details belowshow more

Microsoft just a 1-bit LLM with 2B parameters that... can run on CPUs like Apple M2. BitNet b1.58 2B4T outperforms fp LLaMA 3.2 1B while using only 0.4GB memory versus 2GB and processes tokens 40% faster. 100% opensource.show more