Trending

[R] Block Diffusion: A Hybrid Language Model Combining Autoregressive and Diffusion Approaches for Flexible-Length Generation

The rise of intelligent infrastructure for LLM applications

Llama 3.3 keeping you all safe from sun theft. Thank the Lord.

qwq and gemma-3 added to long context benchmark

I deleted all my previous models after using (Reka flash 3 , 21B model) this one deserve more attention, tested it in coding and its so good

First attempt at AI agent. Where do I start

HowTo: Decentralized LLM on Akash, IPFS & Pocket Network, could this run LLaMA?

KoboldCPP 1.86 just dropped with support of Gemma-3

Qwen

Save item

QwQ-32B

Task: text-generation

DeepSeek

Save item

DeepSeek-R1

Task: text-generation

Google

Save item

gemma-3-1b-it

Task: text-generation

Perplexity

Save item

r1-1776

Task: text-generation

Open R1

Save item

OlympicCoder-7B

Task: text-generation

Open R1

Save item

OlympicCoder-32B

Task: text-generation

Google

Save item

gemma-3-1b-pt

Task: text-generation

Ai2

Save item

OLMo-2-0325-32B-Instruct

Task: text-generation

Qwen

Save item

QwQ-32B-GGUF

Task: text-generation

langchain-ai

Save item

langchain

🦜🔗 Build context-aware reasoning applications

run-llama

Save item

llama_index

LlamaIndex is the leading framework for building LLM-powered agents over your data.

BlinkDL

Save item

RWKV-LM

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.