What could change the answer
- Long context and KV cache
- Batch size or concurrent users
- Runtime overhead and driver support
- CPU/RAM offload
- Image encoders and auxiliary models
MODEL × HARDWARECan RTX 3080 10GB
Can RTX 3080 10GB
run Qwen2.5 14B?
Only with optimization or offload.
Q4_K_M MEMORY VERDICTTIGHT
11.8 GB estimated requirement vs 10.0 GB usable-memory assumption.
Model weights8.9 GB
Runtime reserveIncluded
Hardware stackCUDA
Speed claimNot estimated