Can I run DeepSeek-Coder-V2-Lite-Base on a GeForce RTX 3050?

Figures are GiB of total memory: weights plus KV cache plus compute buffer and backend overhead. Weights and KV are near-exact; the overhead term is modeled. Hover any cell for the breakdown.

The best-fitting configuration above, as a command:

llama-cli -hf deepseek-ai/DeepSeek-Coder-V2-Lite-Base \
  --ctx-size 8192 \
  --cache-type-k q4_0 --cache-type-v q4_0 \
  -ngl auto

Recent llama.cpp defaults to --fit on with -ngl auto, so it will size the offload for you. The question worth your attention is not how many layers to offload but what context and quantization you are willing to live with — which is what the grid above is for.

A parameters × bits ÷ 8 estimate ignores two things that dominate at long context. First, the weights themselves are not the nominal rate — quantizations are mixtures, so the real file is consistently larger than the label implies. Second, this model uses latent attention and allocates no V cache at all, so any formula reading num_key_value_heads overstates its cache by more than an order of magnitude.