RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can deepseek coder 1.3b instruct run on the RTX 4070 Super?

Yes. At 8K context the best fit is F16, using about 4.5 GB of the 11.4 GB usable on the RTX 4070 Super. Estimated speed ceiling: ~187 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.8 GB Fits2.5 GB Fits798
3-bit (Q3_K_M) •1.9 GB Fits2.6 GB Fits715
4-bit (Q4_K_M) •2.0 GB Fits2.8 GB Fits577
5-bit (Q5_K_M) •2.1 GB Fits2.9 GB Fits503
6-bit (Q6_K) •2.3 GB Fits3.1 GB Fits430
8-bit (Q8_0) •2.5 GB Fits3.3 GB Fits352
16-bit (F16/BF16)3.7 GB Fits4.5 GB Fits187

• real GGUF file size from TheBloke/deepseek-coder-1.3b-instruct-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

More

deepseek coder 1.3b instruct on every GPU and Mac · Every model that runs on the RTX 4070 Super · Other models that fit 12 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.