DeepSeek-VL2 Small
DeepSeek-VL2 Small is the middle 16.1B-parameter MoE member of DeepSeek's vision-language family, activating about 2.8B parameters per token. It is designed for visual question answering, OCR, document, table and chart understanding, and visual grounding.
Task Fit
Not marked for code agent in the current library.
Not marked for code in the current library.
General writing, Q&A, and assistant use.
Document QA benefits from long context and instruction following.
Image or visual understanding, not necessarily image generation.
Not marked for image generation in the current library.
Not marked for video generation in the current library.
Not marked for voice in the current library.
Source Confidence
Variants and Quant Artifacts
Choose the artifact first; hardware fit follows from RAM, VRAM, format, and runtime.
| Quant | Format | Quality | Min RAM | Reco RAM | Runtime | Action |
|---|---|---|---|---|---|---|
| BF16 | safetensors | high | 40GB | 48GB | transformers, vllm, sglang | Plan with this |
Recommended Hardware
Lowest estimated 5-year cost that can run this model.
Plenty of fast-memory headroom for this model.
Highest local performance signal among compatible hardware.
Benchmarks
No benchmark data is available for this model yet.
Source and Review
Execution evidence
Run DeepSeek-VL2 Small with a documented recipe
Recipes connect hardware, a model artifact, tools, settings, verification, and a reportable result.
No verified recipe is linked to this record yet.
Compatibility estimates remain available in the planner. A recipe appears here only after its exact stack and verification protocol are documented.
Similar Models
DeepSeek-VL2 is the full 27.5B-parameter MoE vision-language model, activating about 4.5B parameters per token. It provides the strongest capability in the VL2 family for visual question answering, OCR, document, table and chart understanding, and visual grounding.
DeepSeek-VL2 Tiny is the smallest official DeepSeek-VL2 vision-language model. Its 3B-parameter MoE activates about 1B parameters per token and targets visual question answering, OCR, document and chart understanding, and visual grounding with a 4K context window.
DeepSeek V4.1 Flash is DeepSeek's MIT-licensed open-weight multimodal MoE for reasoning, coding, agents, and native image understanding. The complete checkpoint is approximately 763B parameters, including a 552B backbone; its Causal Encoder-Decoder architecture activates 8B parameters during input prefill and 16B during output decoding. CSA2 and FP4 KV caching reduce long-context cache cost. The model supports a 1M-token context window and is available through official FP8 weights, the DeepSeek API, and Ollama Cloud. It remains a data-center-class deployment despite the low active-parameter count.