// DeepSeek · Text LLM
DeepSeek-Coder-V2-Lite-Instruct: VRAM & local deployment
16B total · 2.4B active (MoE) parameters. About 11.4 GB at 4-bit and 36.0 GB at BF16 with one 8K-token request.
released 2024-06-14licence: Commercial with conditionsmemory figures are estimates
01Specs
| Publisher | DeepSeek · deepseek-ai |
|---|---|
| Family / series | DeepSeek · DeepSeek-Coder-Lite |
| Type | Text LLM (text-generation) |
| Parameters | 16B total · 2.4B active (MoE) Source: official model card“DeepSeek-Coder-V2 with 16B and 236B parameters … actived parameters of only 2.4B and 21B” |
| Context length | 160K tokens (163,840)max_position_embeddings in config.json |
| Architecture | 27 layers · MLA · MoE |
| Released weights | BF16 · 31.4 GBdownload |
| Licence | deepseek-license · Commercial with conditionsCommercial use allowed under the publisher’s own licence terms (user caps, acceptable-use policy, attribution or region limits). Read it before shipping. |
| Released | 2024-06-14 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 32.0 GB | 36.0 GB | 36.7 GB | 39.8 GB | 2 × RTX 5090 (64GB) | Mac 64GB |
| FP8 / INT8 / Q8_0 | 17.0 GB | 19.5 GB | 20.2 GB | 23.3 GB | RTX 4090 24GB | Mac 36GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 9.7 GB | 11.4 GB | 12.2 GB | 15.3 GB | 16GB GPU | Mac 24GB |
KV cache per request: 8K 0.3 GB · 32K 1.0 GB · 128K 4.1 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
2 official repo(s) from deepseek-ai.
05Other DeepSeek models
All 34 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| DeepSeek-V4.1-Flash-1017 | 748B / 16B | 499 GB | 2026-10-17 |
| DeepSeek-V4.1-Flash | 748B / 16B | 499 GB | 2026-09-10 |
| DeepSeek-V4-Pro-0813 | 1.65T | 1.10 TB | 2026-08-13 |
| DeepSeek-V4-Flash-0731 | 304.2B | 203 GB | 2026-07-31 |
| DeepSeek-V4-Flash | 284B / 13B | 190 GB | 2026-04-22 |
| DeepSeek-V4-Pro | 1.6T / 49B | 1.07 TB | 2026-04-22 |
| DeepSeek-OCR-2 | 3.39B | 3.3 GB | 2026-01-27 |
| DeepSeek-V3.2 | 685.4B | 458 GB | 2025-12-01 |
06Sources
Data checked 2024-07-03. Parameters, context and licence are copied from the official repository; memory figures are our estimates.