AIモデル一覧
380モデルsが利用可能
AllenAIOLMo 2 13BOLMo 2 13B is AI2's fully open research model with transparent training data and methodology. Designed for reproducible research with competitive performance on reasoning and general knowledge tasks.
CohereCommand R 35BCommand R is Cohere's retrieval-augmented generation model optimized for enterprise use. Excels at long-context document processing, tool use, and grounded generation with citation support.
DeepSeekDeepSeek R1 Distill 70BDeepSeek R1 Distill 70B is a distilled reasoning model based on Llama 70B, offering strong chain-of-thought reasoning at a practical size.
AlibabaQwen 2.5 7BQwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
AlibabaQwen 2.5 Coder 3BCompact coding model with solid code completion and generation for resource-constrained environments.
DeepSeekDeepSeek R1 Distill 32BWe introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing.
MetaCodeLlama 13B InstructCode Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the 13 instruct-tuned version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
Mistral AICodestral Mamba 7BCodestral Mamba is an open code model based on the Mamba2 architecture. It performs on par with state-of-the-art Transformer-based code models. \ You can read more in the official blog post.
DevStral AIDevStral 7BDevstral 7B is Mistral AI's specialized coding model optimized for software development tasks. Features strong code generation, completion, and understanding across multiple programming languages.
IBMGranite Code 8BGranite-8B-Code-Instruct-4K is a 8B parameter model fine tuned from *Granite-8B-Code-Base-4K* on a combination of permissively licensed instruction data to enhance instruction following capabilities including logical reasoning and problem-solving skills.
BigCodeStarCoder 15BStarCoder 15B is BigCode's flagship code generation model trained on 1 trillion tokens from The Stack. Supports 80+ programming languages with 8K context and strong code completion capabilities.
DeepSeekDeepSeek R1 Distill 14BWe introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing.
IBMGranite 4.1 8BGranite 4.1 8B is IBM's sweet-spot dense decoder-only model, trained on roughly 15T tokens with 128K context. IBM reports the 8B instruct model matching or beating the previous Granite 4.0-H-Small 32B-A9B MoE in several comparisons. Apache 2.0 licensed for commercial RAG, coding, and assistant deployments.
Liquid AILFM2.5 8B A1BLFM2.5-8B-A1B is Liquid AI's on-device MoE assistant: 8.3B total parameters with only 1.5B activated per token (32 experts, 4 active). Its hybrid convolution + attention backbone is optimized for fast, low-memory edge inference on consumer hardware.
Mistral AIPixtral 12BThe Pixtral-12B-2409 is a Multimodal Model of 12B parameters plus a 400M parameter vision encoder.
MetaCodeLlama 7B InstructCode Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the 7B instruct-tuned version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
LLaVALLaVA 1.6 13BModel type: LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: mistralai/Mistral-7B-Instruct-v0.2
BigCodeStarCoder 7BStarCoder 7B is BigCode's code generation model trained on The Stack v1. Supports over 80 programming languages with fill-in-the-middle capability and 8K context window.
GoogleGemma 4 E2BGemma 4 E2B is Google's smallest Gemma 4 model with 5.1B total parameters (2.3B effective via Per-Layer Embeddings). Supports text, image, audio, and video natively. Apache 2.0 licensed. Built on Gemini 3 technology.
MistralMinistral 3 3BThe smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
AlibabaQwen 3.5 2BQwen3.5 2B delivers competitive quality at minimal VRAM cost, suitable for laptops and entry-level GPUs.
NVIDIANemotron 70BLlama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
ZhipuGoogleGemma 3 4BGemma 3 4B is Google's efficient Gemma 3 model supporting vision and text. Ideal for on-device applications requiring multimodal understanding with fast inference speeds.