Open Models · Local Deploy

全球开源模型频道

策展 + Ollama Library 全量 + HF GGUF 热门 合并目录:参数/显存、许可、 Hugging Face / GGUF / Ollama / ModelScope 下载,并跳转 本地算力计算器 。HF 全库十万+——本频道做可跑清单、深链与算力账,不镜像权重。 同步于 2026-08-03T07:33:50Z

合并总量325
策展精选42
同步条数303
本地优先318
含 Ollama238
含 HF/GGUF192

全库入口(全球)

要「全部开源」请用下列权威源检索;本站策展负责选型 + 部署路径 + 算力账

按家族

我的显卡一键筛:

匹配 20 · 展示 20 · 点「设为 A/B」后底部一键对比 · 本站不托管权重

minicpm-v

Community · ~7B · unknown · 本地优先 · ollama-library · 5.4M pulls

Q4 ~6GB舒适 12GB

A series of multimodal LLMs (MLLMs) designed for vision-language understanding.

视觉对话
ollama run minicpm-v
mxbai-embed-large

Community · ~1B · unknown · 本地优先 · ollama-library · 13M pulls

Q4 ~0.8GB舒适 2GB

State-of-the-art large embedding model from mixedbread.ai

向量
ollama run mxbai-embed-large
all-minilm

Community · ~1B · unknown · 本地优先 · ollama-library · 3.3M pulls

Q4 ~0.8GB舒适 2GB

Embedding models on very large sentence level datasets.

向量
ollama run all-minilm
snowflake-arctic-embed

Community · ~1B · unknown · 本地优先 · ollama-library · 3.1M pulls

Q4 ~0.8GB舒适 2GB

A suite of text embedding models by Snowflake, optimized for performance.

向量
ollama run snowflake-arctic-embed
bakllava

Community · 7b · unknown · 本地优先 · ollama-library · 871K pulls

Q4 ~6GB舒适 12GB

BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.

视觉对话
ollama run bakllava
bge-large

Community · ~1B · unknown · 本地优先 · ollama-library · 278K pulls

Q4 ~0.8GB舒适 2GB

Embedding model from BAAI mapping texts to vectors.

向量
ollama run bge-large
granite-embedding

Community · ~1B · unknown · 本地优先 · ollama-library · 346K pulls

Q4 ~0.8GB舒适 2GB

The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.

向量代码多语
ollama run granite-embedding
nomic-embed-text-v2-moe

Community · ~1B · unknown · 本地优先 · ollama-library · 627K pulls

Q4 ~0.8GB舒适 2GB

nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.

向量MoE多语
ollama run nomic-embed-text-v2-moe
snowflake-arctic-embed2

Community · ~1B · unknown · 本地优先 · ollama-library · 433K pulls

Q4 ~0.8GB舒适 2GB

Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.

向量多语
ollama run snowflake-arctic-embed2
minicpm-v4.5

Community · ~7B · unknown · 本地优先 · ollama-library · 21K pulls

Q4 ~6GB舒适 12GB

A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

视觉对话
ollama run minicpm-v4.5
minicpm-v4.6

Community · ~7B · unknown · 本地优先 · ollama-library · 26K pulls

Q4 ~6GB舒适 12GB

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

视觉对话
ollama run minicpm-v4.6

与竞品对齐的能力

  • ApX / VRAM 计算器类:本站 /tools/local-deploy 覆盖显存适配、多卡 TP、产出与 vs API 费用。
  • Ollama Library / HF Hub:每条模型直链下载与 ollama run,不二次托管权重。
  • Model Picker(按 GPU 筛模型):列表「显存上限」筛选 + 计算器预填。
  • 价格/中转对照:有 OpenRouter id 的可回 /models · /official-api
Open-source models hub · HF / Ollama / GGUF deploy · GrokCode 倍率榜