← CanIRunLocal · All hardware · All models
Yes, with partial offload (slower). Laguna XS 2.1 33B-A3B (MoE) on RTX 4080 16GB at Q4_K_M uses system RAM (21.4 GB needed, 15.5 GB usable), about 32 tok/s (estimate).
Hardware: RTX 4080 16GB · Model: Laguna XS 2.1 33B-A3B (MoE)
RTX 4080 16GB has 16 GB of VRAM and 717 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 15.5 GB. Partial offload may also use 60% of that system RAM. Laguna XS 2.1 33B-A3B (MoE) (33.4B, 3B active, Poolside) at Q4_K_M is a 20 GB download and needs 21.4 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 20 GB |
| Memory needed | 21.4 GB |
| Usable fast memory | 15.5 GB |
| Fit | partial offload (slower) |
| Estimated speed | ~32 tok/s (estimate) |
| Command | ollama run laguna-xs-2.1:latest |
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