Trending

Optimizing Tool Selection for LLM Workflows with Differentiable Programming

The Right Way to Embed an LLM in a Group Chat

Baba Is Eval

Large Language Models Are Improving Exponentially

Everything around LLMs is still magical and wishful thinking

Gremllm

VLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention

Context Engineering for Agents

High-Fidelity Simultaneous Speech-to-Speech Translation

128GB VRAM for ~$600. Qwen3 MOE 235B.A22B reaching 20 t/s. 4x AMD MI50 32GB.

[d] How do I run mistral 7b locally [help

[R] Post Transformer Architecture R&D

Llama-4-Maverick 402B on a oneplus 13

Powerful 4B Nemotron based finetune

Google finds LLMs can hide secret information and reasoning in their outputs, and we may soon lose the ability to monitor their thoughts

Open source tool for generating training datasets from text files and pdf for fine-tuning language models.

Got some real numbers how llama.cpp got FASTER over last 3-months

THUDM/GLM-4.1V-9B-Thinking looks impressive

Google

Save item

gemma-3n-E4B-it

Task: image-text-to-text

Z.ai & THUKEG

Save item

GLM-4.1V-9B-Thinking

Task: image-text-to-text

Tencent

Save item

Hunyuan-A13B-Instruct

TNG Technology Consulting GmbH

Save item

DeepSeek-TNG-R1T2-Chimera

Task: text-generation

SK Telecom

Save item

A.X-4.0

Task: text-generation

BAIDU

Save item

ERNIE-4.5-21B-A3B-PT

Task: text-generation

SK Telecom

Save item

A.X-4.0-Light

Task: text-generation

K intelligence Mi:dm

Save item

Midm-2.0-Base-Instruct

Task: text-generation

BAIDU

Save item

ERNIE-4.5-0.3B-PT

Task: text-generation