deepseek-v4-pro · Ollama

⇅

Cloud

Embedding

Vision

Tools

Thinking

deepseek-v4-pro

DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a 1M-token context window and three reasoning modes.

tools thinking cloud

112.8K Pulls 1 Tag Updated 1 month ago
deepseek-v4-flash

DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.

tools thinking cloud

111.8K Pulls 1 Tag Updated 1 month ago
saadmanhere/dragonglass

Dragonglass is an autonomous, agentic configuration of the `deepseek-v4-pro:cloud` model. It leverages DeepSeek's 1.6T parameter Mixture-of-Experts architecture and 1M-token context window to execute complex, multi-step workflows with high reliability.

cloud

43 Pulls 1 Tag Updated 1 week ago
rafi-dev/deepseek-v4-pro-max

deepseek v4 pro on max reasoning

cloud

57 Pulls 1 Tag Updated 3 weeks ago
oroboroslabs/deepseek-v4-pro-neuromorph9.6gb

vision tools thinking audio

1 Tag Updated 2 hours ago
oroboroslabs/deepseek-v4-pro-neuromorph3gb

vision tools thinking

1 Tag Updated 2 hours ago
EstebanEscobar/deepseek-v4-pro

tools thinking cloud

1 Tag Updated 4 hours ago
ZimaBlueAI/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

tools thinking

2,582 Pulls 1 Tag Updated 3 weeks ago
huihui_ai/deepseek-v3-pruned

DeepSeek-V3-Pruned-Coder-411B is a pruned version of the DeepSeek-V3 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.

411b

1,389 Pulls 5 Tags Updated 1 year ago