ServingCard logoServingCard

deepseek-coder-v2-lite

deepseek-coder-v2-lite serving configurations from the ServingCard registry.

View on GitHub
Parameters16B (MoE)
ArchitectureDeepSeekV2ForCausalLM
LicenseMIT
Configs1 variant
Observations1
HuggingFace View on HuggingFace →

Benchmark Observations

zenprocessverified
Source

Throughput

58.1 tok/s

Latency

3850ms TTFT

Quality

0.286

GPU

nvidia-gb10

vllm>=0.8.0Unknownfp8-baseline

Fork This Config

Create your own optimized configuration based on these community-verified settings.

Open Configurator

Discussion

Debate benchmarks, share quirks, report what works and what doesn't on your hardware.