← CanIRunLocal · All hardware · All models
Yes, with partial offload (slower). DeepSeek Coder V2 Lite 16B (MoE) on RTX 3080 10GB at Q4_K_M uses system RAM (11 GB needed, 9.5 GB usable), about 62 tok/s (estimate).
Hardware: RTX 3080 10GB · Model: DeepSeek Coder V2 Lite 16B (MoE)
RTX 3080 10GB has 10 GB of VRAM and 760 GB/s of memory bandwidth. The checker holds back 0.5 GB of VRAM for the driver and assumes 16 GB of system RAM, so fast memory usable by Ollama is 9.5 GB. Partial offload may also use 60% of that system RAM. DeepSeek Coder V2 Lite 16B (MoE) (15.7B, 2.4B active, DeepSeek) at Q4_K_M is a 10 GB download and needs 11 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 10 GB |
| Memory needed | 11 GB |
| Usable fast memory | 9.5 GB |
| Fit | partial offload (slower) |
| Estimated speed | ~62 tok/s (estimate) |
| Command | ollama run deepseek-coder-v2:16b-lite-instruct-q4_K_M |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt