DeepSeek-V2-Lite
Open-weights 15.71B-parameter text model from deepseek-ai on Hugging Face (deepseek).
Model by deepseek-ai
Chalk Labs
Need help deploying DeepSeek-V2-Lite?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Pick your client. Read the repository before you give any tool access to your data.
huggingface-cli download deepseek-ai/DeepSeek-V2-Lite
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: model-inference
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Price and limits
Not offered through OpenRouter. Download the weights and run it yourself, or use a host that serves it.
- Provider
- deepseek-ai
- Model id
deepseek-ai/DeepSeek-V2-Lite- Input
- text
- Output
- text
- Tool calling
- Not listed
- Weights
- Open: deepseek-ai/DeepSeek-V2-Lite
- License
- deepseek
- Parameters
- 15.71B
- Downloads
- 146,656 in the last 30 days (Hugging Face)
- Released
- May 15, 2024
Signals
- Hugging Face likes
- 209
- Last release
- Jun 25, 2024 (2 years ago)
From Hugging Face.
Details
- License
- deepseek
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- Hugging Face
More from deepseek-ai
- 0.750score
AGENTS.md · deepseek-ai/deepseek-harness
deepseek-ai
AGENTS.md from deepseek-ai/deepseek-harness: 188 lines covering Pre-stable APIs and released Session data, Repository layout, Commands, Secrets / .env and more.
TemplateAFreshness: A★ 260.4KCodex +5 - 0.583score
DeepSeek-V4-Flash-DSpark
deepseek-ai
Open-weights 165.27B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelCFreshness: COpen weights - 0.497score
DeepSeek-V4-Pro-DSpark
deepseek-ai
Open-weights 1650.5B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelCFreshness: COpen weights - 0.462score
DeepSeek-R1-0528-Qwen3-8B
deepseek-ai
Open-weights 8.19B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelFFreshness: FOpen weights - 0.462score
DeepSeek-R1-Distill-Qwen-7B
deepseek-ai
Open-weights 7.62B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelFFreshness: FOpen weights - 0.462score
DeepSeek-R1-Distill-Qwen-14B
deepseek-ai
Open-weights 14.77B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelFFreshness: FOpen weights
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get DeepSeek-V2-Lite running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
DeepSeek-V2-Lite: price, context window, tool use. Agent Mart. https://agentmart.dev/models/deepseek-ai-deepseek-v2-lite (last updated 2026-10-24)