Can deepseek moe 16b base run on the RTX 3090?
Yes. At 8K context the best fit is Q8_0, using about 18.6 GB of the 22.8 GB usable on the RTX 3090. Estimated speed ceiling: ~311 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) • | 7.7 GB Fits | 808 |
| 3-bit (Q3_K_M) • | 9.4 GB Fits | 639 |
| 4-bit (Q4_K_M) • | 11.6 GB Fits | 499 |
| 5-bit (Q5_K_M) • | 13.0 GB Fits | 437 |
| 6-bit (Q6_K) • | 15.1 GB Fits | 370 |
| 8-bit (Q8_0) • | 17.7 GB Fits | 311 |
| 16-bit (F16/BF16) | 32.0 GB No | — |
• real GGUF file size from mradermacher/deepseek-moe-16b-base-GGUF. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.
More
deepseek moe 16b base on every GPU and Mac · Every model that runs on the RTX 3090 · Other models that fit 24 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/deepseek-moe-16b-base), NVIDIA specs. Data as of 2026-11-17.