Description
DeepSeek V4 Flash is a Mixture-of-Experts model designed for efficient reasoning, coding, and agentic workflows
Stats
18.1K Downloads
3 stars
Capabilities
Minimum system memory
Tags
Last updated
Updated 1 day agobyREADME
DeepSeek V4 Flash
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.
DeepSeek V4 Flash is a Mixture-of-Experts model designed for efficient reasoning, coding, and agentic workflows, with a 1M-token context window.
Highlights
- Agentic capabilities: improved performance on coding-agent and tool-use benchmarks.
- Configurable reasoning: supports thinking mode, with controls for how reasoning content is handled in conversation history.
- Long context: supports up to 1M tokens of context.
- Efficient MoE architecture: uses 284B total parameters with a smaller active parameter count during inference.
Custom Fields
Special features defined by the model author
Enable Thinking
: boolean
(default=true)
Controls whether the model will think before replying.
Drop Thinking
: boolean
(default=false)
Controls whether thinking content is dropped from conversation history.
Parameters
Custom configuration options included with this model
Sources
The underlying model files this model uses
Based on