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 9 · 展示 9 · 点「设为 A/B」后底部一键对比 · 本站不托管权重

nemotron-3-super

NVIDIA · 120b/12b · unknown · 本地优先 · ollama-library · 2.9M pulls

Q4 ~8GB舒适 16GB

NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.

推理MoEAgent对话
ollama run nemotron-3-super
nemotron

NVIDIA · 70b · unknown · 本地优先 · ollama-library · 601K pulls

Q4 ~38.5GB舒适 49GB

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.

Agent对话
ollama run nemotron
nemotron-3-nano

NVIDIA · 4b · unknown · 本地优先 · ollama-library · 662K pulls

Q4 ~4GB舒适 8GB

Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

推理Agent对话
ollama run nemotron-3-nano
nemotron-mini

NVIDIA · ~7B · unknown · 本地优先 · ollama-library · 694K pulls

Q4 ~4GB舒适 8GB

A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.

Agent对话
ollama run nemotron-mini
nemotron3

NVIDIA · ~7B · unknown · 本地优先 · ollama-library · 629K pulls

Q4 ~6GB舒适 12GB

NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.

视觉推理Agent对话
ollama run nemotron3
nemotron-cascade-2

NVIDIA · 30b/3b · unknown · 本地优先 · ollama-library · 138K pulls

Q4 ~4GB舒适 8GB

An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

推理MoEAgent对话
ollama run nemotron-cascade-2
nemotron-3-ultra

NVIDIA · ~7B · unknown · 本地优先 · ollama-library · 37K pulls

Q4 ~4GB舒适 8GB

NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.

推理Agent对话
ollama run nemotron-3-ultra

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