Can DeepSeek Coder V2 Lite Instruct run on the RTX 4080 Super?
Yes. At 8K context the best fit is Q5_K_M, using about 11.9 GB of the 15.2 GB usable on the RTX 4080 Super. Estimated speed ceiling: ~367 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 | 738 |
| 3-bit (Q3_K_M) | 7.9 GB Fits | 8.0 GB Fits | 8.7 GB Fits | 11.5 GB Fits | 566 |
| 4-bit (Q4_K_M) • | 10.4 GB Fits | 10.5 GB Fits | 11.2 GB Fits | 14.0 GB Tight | 419 |
| 5-bit (Q5_K_M) • | 11.8 GB Fits | 11.9 GB Fits | 12.6 GB Fits | 15.4 GB No | 367 |
| 6-bit (Q6_K) • | 13.8 GB Tight | 13.9 GB Tight | 14.6 GB Tight | 17.5 GB No | 309 |
| 8-bit (Q8_0) • | 16.3 GB No | 16.4 GB No | 17.1 GB No | 19.9 GB No | — |
| 16-bit (F16/BF16) | 30.0 GB No | 30.1 GB No | 30.8 GB No | 33.6 GB No | — |
• real GGUF file size from lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF. Speed is a bandwidth ceiling (736 GB/s), not a benchmark. Methodology.
More
DeepSeek Coder V2 Lite Instruct on every GPU and Mac · Every model that runs on the RTX 4080 Super · Other models that fit 16 GB VRAM · 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.