Early days of OpenAI
Early days of OpenAI Jensen Huang once admitted that when NVIDIA unveiled its first AI supercomputer, nobody wanted it. Not a single purchase order. Except for Elon Musk. 'He goes, 'You know what? I h
Knowledge catalogue
Early days of OpenAI Jensen Huang once admitted that when NVIDIA unveiled its first AI supercomputer, nobody wanted it. Not a single purchase order. Except for Elon Musk. 'He goes, 'You know what? I h
Muse Spark Open is live on @huggingface! 🤗 - Strong agentic model (especially for personal agents) - Multimodal from the ground up - 816B parameter model - 42B Active parameters Models link: https://h
I've been reading about all these modders using AI to reverse-engineer games and software. I've been trying out photocraft and gridcraft and have just watched a GTA5 mod featuring Sonic. It's pretty d
https://preview.redd.it/p6i9qifyy8vh1.png?width=2069&format=png&auto=webp&s=2b1e3c7c4fc95f12f0f7d417a4d21410aebfbd35 The 3090 Founders edition has a reputation for hot VRAM. Since LLM token generation
I am an independent researcher. Due to budget constraints, I shifted my 21B MoE pre-training—which I had originally planned to run on 64 H100s—to a single NVIDIA GH200 ($2.29 per hour), and I have com
Thanks for sharing! We open-sourced code and models. 🤗Huggingface Paper: https://huggingface.co/papers/2609.38597 💻 Code: https://github.com/nv-tlabs/PixelUMM 🤗 Model: https://huggingface.co/nvidia/Pi
Benchmarking an LLM here with a NVIDIA RTX 5070 12 GB VRAM here I had been working on a llama.cpp based expert streaming setup for Qwen3.8-Flash-Next 177B (UD-IQ3_XXS) on Windows. Benchmark is about 1
I am trying to import two large datasets to enable statistical analysis. After importing the second dataset, Ollama tells me it has no record of that dataset. Intel i9-11900KF Nvidia 3080Ti 12GB Ubunt
I have been building a somewhat unusual local inference machine around two Huawei Atlas 300I Duo cards. They are relatively inexpensive, passive, dual-accelerator PCIe cards with 96 GB of device memor
I'm part of the Lokutor team that built this. Model: NVIDIA Conformer-CTC Small (13M params, int8). It runs on an ESP32-S3 with 8 MB PSRAM, no GPU or NPU. LibriSpeech WER is 3.7 / 8.2, versus 6.3 / 15
Top tech executives met with President Donald Trump on Tuesday to discuss the future of artificial intelligence amid growing concerns over AI models losing control. Researchers and lawmakers are calli
arXiv:2609.33586v1 Announce Type: new Abstract: On NVIDIA Blackwell B200, tensor-core throughput outpaces special-function exponential throughput by more than two orders of magnitude, exposing exponen
🚨 JUST NOW: Elon Musk and Jensen Huang give an INSIDE LOOK at the big meeting between top AI firms and President Trump today, saying they'll now be 'grading each other's homework' 😆 @elonmusk: 'We sig
arXiv:2609.30846v1 Announce Type: new Abstract: In this paper, we propose I-Parakeet, an integer-only implementation of NVIDIA's Parakeet-CTC (0.6B parameters) that runs on a smartphone NPU without an
Kijai put his magic to good use to improve your MiniMax H3 workflows. The video VAE now encodes up to ~2.2x faster and decodes ~1.4-2.7x faster on Nvidia GPU. Checkout the blog post how to use it: htt
Salesforce Inc. keeps putting all of its eggs in the agent basket — but the strategy appears to be paying off so far. At Dreamforce 2026, Marc Benioff, chief executive officer of Salesforce, bantered
TL;DR: I run a mismatched Tesla V100-PCIE pair—one 16 GB card and one 32 GB card, 48 GB total—in a Proxmox/LXC-based local-inference lab. The practical winner so far is a recent CUDA build of llama.cp
Grok Bot summary of SpaceX CFO Bret Johnsen’s new interview with Tony Kim at SpaceX Mission Control. Bret’s path - Came from semiconductors (Qualcomm, Broadcom; was CFO of MindSpeed) - Barely knew Spa
arXiv:2609.17564v1 Announce Type: new Abstract: Deploying retrieval-augmented generation (RAG) on commodity GPUs such as the NVIDIA T4 (16 GB VRAM) exposes a practical failure mode we call the Compres
arXiv:2609.18310v1 Announce Type: new Abstract: We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages in One Network (SEA-LION) built upon NVIDIA Nemotron 3. The family includes 3
Integrate NVIDIA Resiliency Extension (NVRx) into PyTorch FSDP training on Amazon EKS to overlap checkpoint I/O with training and recover from GPU faults in seconds. This post covers async checkpointi
With the recent Nvidia Huggingface acquisition and frontier AI labs screaming about safety and putting guardrails everywhere, I think it's important that we have local models that aren't affected by a
Nvidia CEO Jensen Huang took a call from President Trump on Monday while onstage at the All-In Podcast's All-In Summit. It's not the first time Huang has taken a call from the president during work, b
Hey everyone — I’m building TensorSharp, an open-source LLM inference engine. Here are the latest DeepSeek V4.1 Flash GGUF results using its native ggml_cuda backend. Setup: 8× NVIDIA A40, layer split
vulkan: support type-aligned GET_ROWS (#28253) vulkan: fall back to CPU for GET_ROWS with misaligned offsets The Vulkan GET_ROWS shader asserts when a tensor's backing-buffer offset plus view_offs is
Hi! Today I'm releasing MageTrail, a Danbooru/E621 proof of concept Full-Finetune of Microsoft's MageFlow 4B T2I model, using a diversity maximized condensed 41k images dataset (originally made by Lod
https://huggingface.co/XHToken/Spark-X2.5-4B-GGUF https://huggingface.co/XHToken/Spark-X2.5-1.7B-GGUF from XHToken: We are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose l
Qwen3.8-Flash-Next (UD-Q4_K_XL) on a single RTX 3090 24GB + 128GB DDR4 — is this config optimal? Hardware CPU: Intel Core i5-12600K RAM: 128 GB DDR4 @ 3600 MHz GPU: NVIDIA RTX 3090, 24 GB VRAM OS: Win
I built a denser GGUF format for ternary models: Q2_B3 / “B3S” If you're running a ternary model like BitNet-b1.58 or Ternary-Bonsai, the weights are already restricted to -1, 0, or +1 times a block s
src : add n_expert_used_max function (#28323) src : add n_expert_used_max function With Commit c61b98b ('model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444)') it is now poss
Jennifer Pattison Tuohy / The Verge: Anker unveils the Eufy MindBase, a local AI hub for its cameras that runs an on-device, Anker-developed LLM, with a dedicated AI chip and up to 48TB of storage — T
arXiv:2609.02684v1 Announce Type: new Abstract: Deploying 3D point cloud models on edge hardware such as the NVIDIA Jetson Orin Nano is severely constrained by compute and memory budgets. Existing com
arXiv:2609.02846v1 Announce Type: new Abstract: Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer E
Today we’re open-sourcing Lily, the local inference engine we built for hybrid compute in Perplexity Computer. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon, built so on-device compute does
arXiv:2608.30076v1 Announce Type: new Abstract: Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integr
arXiv:2608.28113v1 Announce Type: new Abstract: The NVIDIA Blackwell architecture, with native support for the ultra-fine-grained NVFP4 format, opens new opportunities for accelerating large language
I used Claude Code to help write this pipeline - Gemma4 to turn an idea into a short story, then IndexTTS 2.5 running on an NVIDIA 3080 to use voices from LibreVox and VTCK voices to pin as character
arXiv:2608.25192v1 Announce Type: new Abstract: We introduce CRESSim-Neo, a batched GPU simulation engine for surgical robotics and robot learning. CRESSim-Neo combines position-based simulation of ri
AgentX 1.0 is the first fully open‑source multi‑turn agentic coding inference benchmark (Apache 2.0), released August 2026 with a 1 million‑token context and over 1 million tokens of dataset built at
Hi everyone, I'm currently working on optimizing an LLM setup at my company and I'm trying to identify where the actual performance bottleneck is. Our current setup is roughly: LLM: NVIDIA Nemotron mo
Released today: version 1.3 of energygraph Zero build dependencies, lightweight tool for live views of the power-consumption. Version 1.3 adds support for dGPUs from nvidia, intel, amd. Depending on v
Veeda AI, a startup led by a team of former Nvidia Corp. researcher and renowned computer scientist Sanja Fidler, has taken its bow on the main stage after raising 90 million in a seed funding round t
Component Validated configuration Motherboard ASRock Rack SPC621D8U-2T/OVH CPU Xeon Gold 6330 (Get gold/platinum if interested in Optane Pmem gimmicks) GPU fabric Two Broadcom/PLX PEX88096 islands, ei
arXiv:2608.17744v1 Announce Type: new Abstract: Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource
A few weeks after closing a 300 million round backed by Nvidia Corp., Etched Inc. today announced that it has raised an additional 700 million in funding. Investment firm Jane Street led the deal. It
Artificial intelligence startup Groq Inc. today announced that it has raised 350 million in additional funding. The Series A round was led by returning backer Disruptive. Grok stated that Nvidia Corp.
Ollama has the best performance for deepseek v4 flash on average. For local only, you can try qwen3.8 that is optimized: Apple Silicon: ollama run qwen3.8:27b-mlx NVIDIA: ollama run qwen3.8:27b Benchm
Tool: CORS Chat I built this today (with GPT-5.6-Sol xhigh) to help test Qwen 3.8 27B running in LM Studio on both my M5 MacBook Pro and an NVIDIA DGX Spark. It provides a web UI for exercising an Ope
Georgi Gerganov showcased running a LLaMA server on an NVIDIA DGX‑Spark, serving the Qwen 3.8‑27B model in GGUF format (`ggml-org/Qwen3.8-27B-GGUF`). The command demonstrates two quantization options—
Qwen3.8-2.4T-A95B is now live on Fireworks with Day-0 support! This 2.4T parameter MoE model is built for autonomous agents, heavy coding, large context windows, and is ideal for coding and agentic pe
Cade Metz / New York Times: xAI co-founder Igor Babuschkin's River AI raised $1B led by General Catalyst to build home or small business computer servers capable of running AI locally — Igor Babuschki
Muse Glimmer Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other plat
v0.32.8 is an Oct 10, 2023 release of the ollama repository on GitHub, following a pre‑release tag v0.32.8‑rc0. The update adds Muse Glimmer support for NVIDIA, AMD and additional platforms, with the
There are already plenty of different extensions for voice input, but all I found required having a second server running. I wanted something super simplistic: launching local STT server just for my p
arXiv:2608.06088v1 Announce Type: new Abstract: Robotics simulators serve as a foundational infrastructure for embodied AI, facilitating safe and scalable robotic system development. NVIDIA Isaac Sim
High-performance inference of NVIDIA's Parakeet TDT 0.6B V2 English transcription model, in the browser. Check out the live demo: https://parakeet.narcotic.sh/ A fully custom, dependancy-free implemen
First of all, my setup: Ryzen 9 5950x DDR4 3200Mhz 64gb (2x32) Dual 3090s, no NVLINK Runtime: llama.cpp Nvidia Drivers 610 Windows 11 25H2 Qwen 3.6 27B Q8 I've been using llama-server with --split-mod
arXiv:2608.05138v1 Announce Type: cross Abstract: Modern Greek is absent from NVIDIA's Nemotron retrieval models and from major multilingual retrieval benchmarks, despite being important for retrieval
Ran DeepSeek V4-Flash-0731 — the full official checkpoint, not a re-quant — on commodity used hardware. Sharing because I couldn't find anyone else publishing Ampere results for this engine. Why bothe
The math still ain’t mathing. Recently we estimated global (ex China) AI revenues of around 200bn annualised, based on four different sources. Just come across a fifth, based on Nvidia inference sales