← CanIRunLocal · All hardware · All models
No. Llama 4 Scout 109B (MoE) does not fit on RTX 5090 32GB: Q4_K_M needs 69.7 GB and 31.5 GB is usable.
Hardware: RTX 5090 32GB · Model: Llama 4 Scout 109B (MoE)
RTX 5090 32GB has 32 GB of VRAM and 1792 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 31.5 GB. Partial offload may also use 60% of that system RAM. Llama 4 Scout 109B (MoE) (109B, 17B active, Meta) at Q4_K_M is a 67 GB download and needs 69.7 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 67 GB |
| Memory needed | 69.7 GB |
| Usable fast memory | 31.5 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run llama4:16x17b |
Smallest hardware that runs it: M2 Max (38c GPU) 96GB at Q4_K_M (fits in fast memory, 69.7 GB needed, 72.0 GB usable, about 15 tok/s (estimate)). Can a M2 Max (38c GPU) 96GB run Llama 4 Scout 109B (MoE)?
A smaller Meta model that fits this hardware: Llama 3.2 Vision 11B at Q8_0 (fits in fast memory, 13.5 GB). Can a RTX 5090 32GB run Llama 3.2 Vision 11B?
Open RTX 5090 32GB in the checkerEstimates, 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