RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek V4 Flash run on the A100 40GB?

No. Even at 2-bit with 8K context, DeepSeek V4 Flash needs about 103 GB, more than the 38.0 GB usable on the A100 40GB.

Newer compressed-attention design: long-context figures are an upper bound.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)103 GB No103 GB No105 GB No114 GB No—
3-bit (Q3_K_M)133 GB No134 GB No136 GB No145 GB No—
4-bit (Q4_K_M)167 GB No167 GB No169 GB No178 GB No—
5-bit (Q5_K_M)194 GB No194 GB No197 GB No206 GB No—
6-bit (Q6_K)223 GB No224 GB No226 GB No235 GB No—
8-bit (Q8_0)289 GB No289 GB No292 GB No301 GB No—
16-bit (F16/BF16)543 GB No543 GB No546 GB No555 GB No—

• real GGUF file size. Speed is a bandwidth ceiling (1555 GB/s), not a benchmark. Methodology.

Hardware that does fit it

DGX SparkRyzen AI Max+ 395 128GBH200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB

More

DeepSeek V4 Flash on every GPU and Mac · Every model that runs on the A100 40GB · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/DeepSeek-V4-Flash), NVIDIA specs. Data as of 2026-11-17.