Can DeepSeek Coder V2 Lite Instruct run on the 2x RTX 3090?
Yes. At 8K context the best fit is F16, using about 30.1 GB of the 45.6 GB usable on the 2x RTX 3090. Estimated speed ceiling: ~176 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 6.2 GB Fits | 6.3 GB Fits | 7.0 GB Fits | 9.9 GB Fits | 938 |
| 3-bit (Q3_K_M) | 7.9 GB Fits | 8.0 GB Fits | 8.7 GB Fits | 11.5 GB Fits | 720 |
| 4-bit (Q4_K_M) • | 10.4 GB Fits | 10.5 GB Fits | 11.2 GB Fits | 14.0 GB Fits | 533 |
| 5-bit (Q5_K_M) • | 11.8 GB Fits | 11.9 GB Fits | 12.6 GB Fits | 15.4 GB Fits | 466 |
| 6-bit (Q6_K) • | 13.8 GB Fits | 13.9 GB Fits | 14.6 GB Fits | 17.5 GB Fits | 393 |
| 8-bit (Q8_0) • | 16.3 GB Fits | 16.4 GB Fits | 17.1 GB Fits | 19.9 GB Fits | 331 |
| 16-bit (F16/BF16) | 30.0 GB Fits | 30.1 GB Fits | 30.8 GB Fits | 33.6 GB Fits | 176 |
• real GGUF file size from lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.
More
DeepSeek Coder V2 Lite Instruct on every GPU and Mac · Every model that runs on the 2x RTX 3090 · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct), NVIDIA specs. Data as of 2026-11-17.