RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek coder 7b instruct v1.5 run on the DGX Spark?

Yes. At 8K context the best fit is F16, using about 17.2 GB of the 109 GB usable on the DGX Spark. Estimated speed ceiling: ~20 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •5.0 GB Fits100
3-bit (Q3_K_M) •5.7 GB Fits79
4-bit (Q4_K_M) •6.4 GB Fits65
5-bit (Q5_K_M) •7.1 GB Fits55
6-bit (Q6_K) •7.8 GB Fits48
8-bit (Q8_0)9.3 GB Fits37
16-bit (F16/BF16)15.3 GB Fits20

• real GGUF file size from mradermacher/deepseek-coder-7b-instruct-v1.5-i1-GGUF. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.

More

deepseek coder 7b instruct v1.5 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-7b-instruct-v1.5), NVIDIA specs. Data as of 2026-11-17.