Can deepseek vl2 tiny run on the RTX 3090 Ti?
Yes. At 8K context the best fit is F16, using about 7.4 GB of the 22.8 GB usable on the RTX 3090 Ti. Estimated speed ceiling: ~429 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) | 2.1 GB Fits | 2287 |
| 3-bit (Q3_K_M) | 2.4 GB Fits | 1755 |
| 4-bit (Q4_K_M) | 2.8 GB Fits | 1403 |
| 5-bit (Q5_K_M) | 3.1 GB Fits | 1204 |
| 6-bit (Q6_K) | 3.5 GB Fits | 1046 |
| 8-bit (Q8_0) | 4.2 GB Fits | 807 |
| 16-bit (F16/BF16) | 7.2 GB Fits | 429 |
• real GGUF file size. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.
More
deepseek vl2 tiny on every GPU and Mac · Every model that runs on the RTX 3090 Ti · Other models that fit 24 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/deepseek-vl2-tiny), NVIDIA specs. Data as of 2026-11-17.