Can deepseek moe 16b base run on the RTX 6000 Ada?
Yes. At 8K context the best fit is F16, using about 32.8 GB of the 45.6 GB usable on the RTX 6000 Ada. Estimated speed ceiling: ~170 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) • | 7.7 GB Fits | 829 |
| 3-bit (Q3_K_M) • | 9.4 GB Fits | 655 |
| 4-bit (Q4_K_M) • | 11.6 GB Fits | 512 |
| 5-bit (Q5_K_M) • | 13.0 GB Fits | 449 |
| 6-bit (Q6_K) • | 15.1 GB Fits | 379 |
| 8-bit (Q8_0) • | 17.7 GB Fits | 319 |
| 16-bit (F16/BF16) | 32.0 GB Fits | 170 |
• real GGUF file size from mradermacher/deepseek-moe-16b-base-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.
More
deepseek moe 16b base on every GPU and Mac · Every model that runs on the RTX 6000 Ada · Other models that fit 48 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.