Latest Announcements
Deepseek OCR: Vision‑Language Compression Meets Dynamic OCR
Published on 2025-11-19
More News
Trending Models
Gpt Oss 120B
GPT-OSS 120B by OpenAI: 120 billion param. model for complex reasoning tasks, supports English only.
Gpt Oss 20B
GPT-OSS 20B: OpenAI's 20 billion parameter model for low-latency, local applications. Mono-linguistic.
Qwen3 8B
Qwen3 8B: Alibaba's 8 billion parameter LLM for reasoning & problem-solving. Mono-lingual model with context lengths up to 8k.
Qwen3 Coder 30B
Qwen3 Coder 30B: Alibaba's 30 billion param LLM for agentic coding, supports mono-lingual contexts up to 2,5,6,k.
Llama3.2 3B Instruct
Llama3.2 3B Instruct by Meta Llama Enterprise: A multilingual, 3 billion parameter model with 8k to 128k context-length, designed for assistant-like chat apps.
Qwen3 0.6B
Qwen3 0.6B: Alibaba's 0.6 billion param model excels in reasoning tasks with a 32k context window.
Deepseek R1 671B
Deepseek R1 671B: Bi-lingual Large Language Model with 671 billion parameters. Supports context lengths up to 128k for advanced code generation and debugging tasks.
Llama3.2 1B Instruct
Llama3.2 1B Instruct by Meta Llama Enterprise: A versatile, multilingual large language model with 1 billion parameters and context lengths up to 128k, designed for assistant-like chat applications.
Llama3.2 1B
Llama3.2 1B: Meta's 1B param model for multilingual chat apps, with context lengths up to 128k.
Qwen2.5 3B Instruct
Qwen2.5 3B Instruct: Alibaba's multilingual LLM with 3B params, 32k/8k context-length, excels in long text generation.
Qwen2.5 1.5B Instruct
Qwen2.5 Instruct: Alibaba's 1.5B param model for multilingual long text generation up to 32k tokens.
Qwen2.5Vl 7B
Qwen2.5VL 7B: Alibaba's 7 billion parameter LLM for visual content analysis.
