DeepSeek Coder
#24 in Open-Source-Spraakmodelledeepseek · siet November 2023 · 4× · tolest 02. Juli 2026
26
Momentum
DeepSeek Coder is a code-specialized model. It is offered at a price of $0.25.
Momentum-Verloop
04.04.03.07.
Features
| Benchmark Score (MMLU/Similar) | HumanEval: 79.3% (DeepSeek-Coder-33B-Instruct, v1); DeepSeek-Coder-V2: HumanEval 90.2%, MBPP 76.2%, LiveCodeBench 43.4% |
| Inference Speed | DeepSeek-Coder-V2 Lite (16B MoE): ~12 tokens/sec in single-stream mode; ~150 tokens/sec at batch size 28 (user-reported figures, MoE architecture favors batch processing) |
| Context Window | 16,000 tokens (16K) |
| Model Size (Parameters) | 1.3B to 33B parameters (8 variants: 1.3B, 5.7B, 6.7B, 7B, 33B; each in Base and Instruct) |
| Memory Requirement | DeepSeek-Coder-V2 Lite (16B MoE, 2.4B active): ~32 GB weights at FP16; fits on a single 16 GB GPU (e.g., RTX 4060 Ti) at INT4. 236B variant requires multiple 96 GB cards. |