Best MiniCPM-2B Alternatives in 2025
-
With a total of 8B parameters, the model surpasses proprietary models such as GPT-4V-1106, Gemini Pro, Qwen-VL-Max and Claude 3 in overall performance.
-
MiniCPM3-4B is the 3rd generation of MiniCPM series. The overall performance of MiniCPM3-4B surpasses Phi-3.5-mini-Instruct and GPT-3.5-Turbo-0125, being comparable with many recent 7B~9B models.
-
Build AI models from scratch! MiniMind offers fast, affordable LLM training on a single GPU. Learn PyTorch & create your own AI.
-
SmolLM is a series of state-of-the-art small language models available in three sizes: 135M, 360M, and 1.7B parameters.
-
PolyLM is a multilingual large language model designed to address the gaps and limitations in curren
-
iconicon嘻哈歌手arrow56/5000iconMiniMax is the latest generation of large-scale Chinese language models, and its main goal is to help humans write efficiently, stimulate creativity, acquire knowledge, and make decisions.
-
Qwen2.5 series language models offer enhanced capabilities with larger datasets, more knowledge, better coding and math skills, and closer alignment to human preferences. Open-source and available via API.
-
Yuan2.0-M32 is a Mixture-of-Experts (MoE) language model with 32 experts, of which 2 are active.
-
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
-
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
-
CentML streamlines LLM deployment, reduces costs up to 65%, and ensures peak performance. Ideal for enterprises and startups. Try it now!
-
Mini-Gemini supports a series of dense and MoE Large Language Models (LLMs) from 2B to 34B with image understanding, reasoning, and generation simultaneously. We build this repo based on LLaVA.
-
ChatGLM-6B is an open CN&EN model w/ 6.2B paras (optimized for Chinese QA & dialogue for now).
-
Enhance vision-language understanding with MiniGPT-4. Generate image descriptions, create websites, identify humor elements, and more! Discover its versatile capabilities.
-
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
OneLLM is your end-to-end no-code platform to build and deploy LLMs.
-
DeepSeek LLM, an advanced language model comprising 67 billion parameters. It has been trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese.
-
Explore InternLM2, an AI tool with open-sourced models! Excel in long-context tasks, reasoning, math, code interpretation, and creative writing. Discover its versatile applications and strong tool utilization capabilities for research, application development, and chat interactions. Upgrade your AI landscape with InternLM2.
-
Enhance your NLP capabilities with Baichuan-7B - a groundbreaking model that excels in language processing and text generation. Discover its bilingual capabilities, versatile applications, and impressive performance. Shape the future of human-computer communication with Baichuan-7B.
-
Enhance language models, improve performance, and get accurate results. WizardLM is the ultimate tool for coding, math, and NLP tasks.
-
Discover PaLM 2, Google's advanced language model for reasoning, translation, and coding tasks. Built with responsible AI practices, PaLM 2 excels in multilingual collaboration and specialized code generation.
-
OpenBMB: Building a large-scale pre-trained language model center and tools to accelerate training, tuning, and inference of big models with over 10 billion parameters. Join our open-source community and bring big models to everyone.
-
GLM-4-9B is the open-source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI.
-
Enhance language models with Giga's on-premise LLM. Powerful infrastructure, OpenAI API compatibility, and data privacy assurance. Contact us now!
-
WordLlama is a utility for natural language processing (NLP) that recycles components from large language models (LLMs) to create efficient and compact word representations, similar to GloVe, Word2Vec, or FastText.
-
OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain.
-
Easyest and lazyest way for building multi-agent LLMs applications.
-
Discover StableLM, an open-source language model by Stability AI. Generate high-performing text and code on personal devices with small and efficient models. Transparent, accessible, and supportive AI technology for developers and researchers.
-
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models.