deepseek-ai · deepseek_v2
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek-Coder-V2-Lite-Instruct by deepseek-ai: a 15.7B-parameter mixture-of-experts open-weight model under the other license.
931,690 downloads · 663 likes · Model card · synced 2026-09-22
Specifications
- Parameters
- 15.7B (1.5B active)
- Architecture
- moe · deepseek_v2
- Layers
- 27
- Hidden size
- 2,048
- KV heads · head dim
- 16 · 128
- Vocabulary
- 102,400
- Native dtype
- bfloat16
- Context window
- 163,840 tokens
- Released
- 2024-06-14
- Last modified on Hub
- 2024-07-03
Features & licensing
- License
- other
- Commercial use
- No
- Modalities
- text
- Tool / function calling
- No
- Reasoning mode
- No
- Languages
- EN
- Quantised variants on Hub
- —
- Pipeline
- text-generation
Task fit
Editorial scores (0–100) used by the recommendation engine.
- Chat70
- RAG / Q&A70
- Code70
- Summarisation70
- Extraction70
- Agents70
Hardware to run DeepSeek-Coder-V2-Lite-Instruct
Weights need about 35 GB at FP16, 18 GB at INT8 and 10 GB at INT4. The KV cache adds roughly 221 MB per 1,000 tokens per request. For a reference workload of 5 requests per second with 1,500 input and 300 output tokens, total GPU memory is around 16.7 GB, which fits on 1 × NVIDIA A100 (80 GB).
| Configuration | VRAM | Utilisation | Est. first token | Cloud / month |
|---|---|---|---|---|
| 1 × NVIDIA L4 (24 GB) | 24 GB | 70 % | ~0.5 s | $584 |
| 1 × NVIDIA L40S (48 GB) | 48 GB | 35 % | ~0.2 s | $1,387 |
| 1 × NVIDIA A100 (80 GB)recommended | 80 GB | 21 % | ~0.1 s | $2,336 |
| 1 × NVIDIA H100 (80 GB) | 80 GB | 21 % | ~0.0 s | $3,285 |
Estimates only. Run an assessment for your own traffic.
Auto-imported from Hugging Face. Architecture, license and feature data are synced from the model repository; the task-fit scores below are provisional defaults until a curator reviews them.