Trending

llamafile: Distribute and Run LLMs with a Single File

SSE sucks for transporting LLM tokens

From Text to Token: How Tokenization Pipelines Work

Training LLMs for Honesty via Confessions

GPT-5.2

Dependent Names with a Little Encouragement

GPT-5.2

Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) and Vibe CLI

224× Compression of Llama-70B with Higher Accuracy (Paper and Code)

New Google model incoming!!!

NVIDIA releases Nemotron 3 Nano, a new 30B hybrid reasoning model!

Qwen3-Next-80B-A3B-Thinking-GGUF has just been released on HuggingFace

Google screwed itself (gemini) with their love for keyword soup. Lol.

i vibe coded a 6m param model using one prompt to gemini (no dataset nothing gemini does it all)

OpenAI's flagship model, ChatGPT-5.2 Thinking, ranks most censored AI on Sansa benchmark.

[D] How does Claude perform so well without any proprietary data?

NVIDIA gpt-oss-120b Eagle Throughput model

Running an LLM on a 3DS

Z.ai

Save item

GLM-4.6V-Flash

Task: image-text-to-text

Microsoft

Save item

VibeVoice-Realtime-0.5B

Task: text-to-speech

Mistral AI_

Save item

Devstral-Small-2-24B-Instruct-2512

Z.ai

Save item

GLM-TTS

Task: text-to-speech

ServiceNow-AI

Save item

Apriel-1.6-15b-Thinker

Task: image-text-to-text

NVIDIA

Save item

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Task: text-generation

NVIDIA

Save item

Nemotron-Orchestrator-8B

Task: text-generation

ByteDance

Save item

Dolphin-v2

Task: image-text-to-text

OpenThoughts

Save item

OpenThinker-Agent-v1

Task: text-generation

f

Save item

awesome-chatgpt-prompts

Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

langchain-ai

Save item

langchain

🦜🔗 The platform for reliable agents.

NVIDIA

Save item

Megatron-LM

Ongoing research training transformer models at scale

openai

Save item

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

microsoft

Save item

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

huggingface

Save item

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

deepspeedai

Save item

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

ggml-org

Save item

whisper.cpp

Port of OpenAI's Whisper model in C/C++

huggingface

Save item

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more