SkillsHooksPromptsAgentsPersonasModelsPoliciesToolsTemplatesBundlesCategoriesStart here
← Models
Mo modelreasoningaistable

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.

id model/deepseek-v4-flashvendor DeepSeekfamily DeepSeek-V
Capabilities
toolsthinkingcloud
Model card
https://ollama.com/library/deepseek-v4-flash ↗

Providers

ProviderModel idGet itTagsPullsUpdated
Ollama ↗deepseek-v4-flashollama pull deepseek-v4-flash2420K2026-08-01

Same family

ollamalocaltoolsthinkingcloud
Author DeepSeek. Source ollama.com/library (original ↗). License unknown — the source states none; review before redistributing. Imported 2026-09-03. Description, capabilities, sizes, pulls, tag count and updated date as shown on the Ollama library page. Vendor, family and task are inferred from the model name; weights license is not published on the listing.