Language model optimization

Models 7

• Gen 3
  DiffusionGemma

  By Google

  DiffusionGemma is Google’s open experimental 26B MoE text-diffusion model for faster local text generation, parallel editing, code infilling, and non-linear text workflows.

  💬Chatting🔄Language model optimization🧠AI inference
  NewMultimodal

  Released 1mo ago
• Gen 7 Apertus
  Apertus v1.1 1.5B

  By Swiss AI Initiative

  Apertus-v1.1-1.5B is a 1.5 billion parameter base language model trained via distillation from an 8B teacher model. It supports 1,811 languages, uses a dense transformer architecture with grouped-query attention and xIELU activation, and has a 32,768 token context window. Designed for text generation and multilingual applications.

  📚Large Language Models🌍Translations🔄Language model optimization
  NewText

  Released 2mo ago
• Gen 7
  F pre 8kv 8k 14k SWA

  By Ai2

  F_pre_8kv_8k_14k_SWA is an AllenAI OlmPool architectural-variation model for studying long-context extension. It is a 7B to 8B class language model trained to 150B tokens total, including 140B pretraining and 10B context extension, and is meant for research on architecture choices rather than polished instruction-following use.

  📚Large Language Models🔄Language model optimization
  Text

  Released 3mo ago
• Gen 3 Gemma
  Gemma 4 31B IT NVFP4

  By NVIDIA

  Gemma-4-31B-IT-NVFP4 is NVIDIA’s inference-optimized NVFP4 quantized version of Gemma 4 31B IT. It is a commercial-ready multimodal model for text, image, and video understanding with text output, built for reasoning, coding, chat, and agentic workflows while preserving the original model’s long 256K context window.

  🔄Language model optimization🔍Image interpretation🧠AI inference
  Multimodal

  Released 3mo ago
• Gen 7
  LFM2.5 350M

  By Liquid AI

  LFM2.5-350M is Liquid AI’s compact 350M-parameter language model optimized for fast inference, tool use, data extraction, and structured outputs. It is designed to run across cloud GPUs, CPUs, and edge devices, and is positioned for lightweight agentic workflows and large-scale data processing rather than math, coding, or creative writing.

  📚Large Language Models🔍Data extraction🔄Language model optimization🧠AI inference
  Text

  Released 3mo ago
• Gen 7
  Mamba-3

  By Together AI

  Mamba-3 is a new state space model (SSM) architecture designed with inference efficiency as the primary goal, improving prefill and decode latency across sequence lengths.

  🔨LLM development🎓LLM training🔄Language model optimization🧠AI inference
  Text

  Released 4mo ago
• Gen 7
  Sequential Hidden Decoding 8B n8

  By Tencent

  Sequential-Hidden-Decoding-8B-n8 is Tencent’s base language model variant that extends effective sequence length by 8x using multiple embedding passes while keeping the same Transformer backbone. Built on Qwen3-8B-Base, it is aimed at benchmarking, text completion, and fine-tuning research, with hidden latent steps acting like implicit reasoning before each predicted token.

  📚Large Language Models🤖Ai research assistance🔄Language model optimization🧠AI inference
  Text

  Released 4mo ago