RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek coder 1.3b instruct run on the DGX Spark?

Yes. At 8K context the best fit is F16, using about 4.5 GB of the 109 GB usable on the DGX Spark. Estimated speed ceiling: ~101 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.8 GB Fits2.5 GB Fits432
3-bit (Q3_K_M) •1.9 GB Fits2.6 GB Fits387
4-bit (Q4_K_M) •2.0 GB Fits2.8 GB Fits313
5-bit (Q5_K_M) •2.1 GB Fits2.9 GB Fits272
6-bit (Q6_K) •2.3 GB Fits3.1 GB Fits233
8-bit (Q8_0) •2.5 GB Fits3.3 GB Fits191
16-bit (F16/BF16)3.7 GB Fits4.5 GB Fits101

• real GGUF file size from TheBloke/deepseek-coder-1.3b-instruct-GGUF. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.

More

deepseek coder 1.3b instruct on every GPU and Mac · Every model that runs on the DGX Spark · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/deepseek-coder-1.3b-instruct), NVIDIA specs. Data as of 2026-11-17.