TensorRT 206% faster than llama.cpp ✳️ We wired NVIDIA... AI's TensorRT into Atomic Chat's engine and tested Qwen3.5-4B/Qwen 3-8B via CUDA on a Blackwell RTX 5090, measuring 3.43s vs 10.49s with llama.cpp Run AI models locally ->show more

Running MiniCPM5-2B locally on a 16GB MacBook 💻 It... beats Qwen3.5-4B on benchmarks, so we asked it to find recent AI news, it called web search, pulled back 10 results and summarized the key developments inside Atomic Chat Run local models viashow more

Qwen 3.6 models are now 2.5x times faster on... Atomic Chat with new MTP speedups. > MTP drafts several tokens ahead and verifies them in one pass. The speedup depends on the memory moved per pass. Users can run Qwen 3.6 models locally via the open-source Atomic Chat to test them!show more

Run Ternary Bonsai 2 locally in Atomic Chat 🪴... PrismML shrank Qwen3.5 7x so the 9B goes from 17.9 GB to just 2.42 GB and it keeps up or outperforms the original model on benchmarks Run AI models locally ->show more

it’s so smooth (Nvidia TensorRT optimized)

Qwen3.5-35B-A3B is now in Jan 🔥 It surpasses previous... Qwen3 models more than 6× its size. Get the latest Jan at Thanks to Qwen for the base model and Georgi Gerganov for llama.cpp 💛show more

Run Uncensored Qwen-Image 2.1 on 16GB Mac Qwen's image... model with no filters makes the images cloud apps refuse and your prompts never leave your Mac, all of it done locally Run AI models locally ->show more

Qwen3.6-27B-Base looping so hard, I've run out of context... and scrollback. Left like this for a good 30 minutes wasting electricity on my spendy UK tariff ⚡️ 🤑 Unsloth AI's Q8 UD XL quant of Qwen and llama.cpp - fp16 kv cache - driven by opencode 1/2show more

Qwen3.5-4B searched 20+ websites, cited its sources, and found... the best answer! 🔥 Try this locally with just 4GB RAM via Unsloth Studio. The 4B model did this by executing tool calls + web search directly during its thinking trace.show more

Trained a simple world model for my robot arm.... It predicts the future over 20000 times faster than real time on a single NVIDIA RTX 3090 GPU (128 batch -> 160x faster each).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

Ready to get started with visual generative AI? Look... no further. Learn how to run image and video models locally on RTX GPUs using ComfyUI with LTX & BlackForestLabsAI - Unofficial FLUX in our blog below. 👇show more

1/8) FastVideo FastH3 now runs on a single consumer... machine: NVIDIA RTX GPUs 💚, DGX Spark and Apple Silicon 🍎 FastH3 V2 beats base MiniMax (official) H3 in 8 steps. A 5 s 480p clip with audio takes 15 s on one RTX 5090. We also release FastH3 Trim: 4.2× smaller than base H3, and it runs in as little as 8 GB of GPU memory. Every clip here was generated locally. NVIDIAAI NVIDIARTXSparkshow more

Local Laya blitzed other models on RTX 4090 ⚡️... Four local decision models raced down Wikipedia picking out every word that names a centipede and Laya took 3.9 ms a word so it ended up being the fastest overall Run decision models locally ->show more

gpt-oss-20b is lightning fast on a NVIDIA RTX 5090.... I get around 160-180 tokens per second.show more

Demo of 1-bit Bonsai 8B from PrismML running on-device... on iPhone 17 Pro More than 40tk/s for a dense 8B model on iPhone, that’s a first Powered by Apple MLX and available now in Locally AIshow more

We heard you like seafood 🦞. Meet the workstation... of the AI era: The Dell Pro Max with GB300 and @NVIDIA NemoClaw. You can run AI agents locally, securely & nonstop.show more

We made it easy to run local models on... your computer and use them from your phone. A secure, end-to-end encrypted connection in just a few clicks. Available now with LM Studio and Locally AI - Local AI Chat.show more

MiniMax M3.1 Flash vs DeepSeek at Tesla Roadster 🚔... MiniMax M3.1 Flash re-created this viral Tesla Roadster police chase scene for $2.34, while DeepSeek V4.1 Flash's version cost $3.07 Run AI models locally or via API ->show more