RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek V2 Chat run on the H200?

Yes. At 8K context the best fit is Q3_K_M, using about 108 GB of the 134 GB usable on the H200. Estimated speed ceiling: ~459 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)83.2 GB Fits83.5 GB Fits85.0 GB Fits91.4 GB Fits599
3-bit (Q3_K_M)108 GB Fits108 GB Fits110 GB Fits116 GB Fits459
4-bit (Q4_K_M)135 GB No135 GB No137 GB No143 GB No—
5-bit (Q5_K_M)157 GB No158 GB No159 GB No165 GB No—
6-bit (Q6_K)181 GB No181 GB No183 GB No189 GB No—
8-bit (Q8_0)234 GB No234 GB No236 GB No242 GB No—
16-bit (F16/BF16)440 GB No440 GB No442 GB No448 GB No—

• real GGUF file size. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.

More

DeepSeek V2 Chat on every GPU and Mac · Every model that runs on the H200 · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/DeepSeek-V2-Chat), NVIDIA specs. Data as of 2026-11-17.