Model Library
DeepSeekReleased June 17, 2024DeepSeek Coder V2 Lite
DeepSeek · Released June 17, 2024
Intelligence score
3
At a glance
- Intelligence
- 3
- Speed
- —
- Latency
- —
- Input price
- Not published
- Output price
- Not published
- Context window
- 130Ktokens
- Parameters
- 16billions
Summary
Comparison summary
DeepSeek Coder V2 Lite Instruct scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 6).
Specifications
Technical specifications
| Model name | DeepSeek Coder V2 Lite |
|---|---|
| Provider | DeepSeek |
| Release date | June 17, 2024 |
| Intelligence score | 3 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | Not published |
| Output price | Not published |
| Context window | 130,000 tokens |
| Parameters | 16B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | DEEPSEEK LICENSE AGREEMENT |
| API availability | — |
| Source | Model Intelligence legacy profile: deepseek-coder-v2-lite |
FAQ · 16
Frequently asked questions
DeepSeek Coder V2 Lite Instruct was released on June 17, 2024.
DeepSeek Coder V2 Lite Instruct was created by DeepSeek.
DeepSeek Coder V2 Lite Instruct scores 3 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 6).
No, DeepSeek Coder V2 Lite Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
DeepSeek Coder V2 Lite Instruct supports text only input.
DeepSeek Coder V2 Lite Instruct supports text only output.
No, DeepSeek Coder V2 Lite Instruct does not support image input. It can only process text.
No, DeepSeek Coder V2 Lite Instruct is not multimodal. It only supports text only input.
DeepSeek Coder V2 Lite Instruct has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, DeepSeek Coder V2 Lite Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
DeepSeek Coder V2 Lite Instruct has 16 billion parameters (2.4 billion active).
DeepSeek Coder V2 Lite Instruct is a Mixture of Experts (MoE) model with 16 billion total parameters, but only 2.4 billion active parameters are used during inference.
DeepSeek Coder V2 Lite Instruct is released under the DEEPSEEK LICENSE AGREEMENT license. This license allows commercial use.
DeepSeek Coder V2 Lite Instruct achieves a score of 3 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
DeepSeek Coder V2 Lite Instruct is an open weights model that can be self-hosted.
DeepSeek Coder V2 Lite Instruct is an open weights model that can be downloaded and self-hosted.