← CanIRunLocal · All hardware · All models
Yes. Nemotron 3.5 Bolt 74B-A9B (MoE, IQ2-class) fits in fast memory on RTX 5090 32GB at Default (27.7 GB needed, 31.5 GB usable), about 177 tok/s (estimate).
Hardware: RTX 5090 32GB · Model: Nemotron 3.5 Bolt 74B-A9B (MoE, IQ2-class)
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. Nemotron 3.5 Bolt 74B-A9B (MoE, IQ2-class) (74B, 9B active, NVIDIA) at Default is a 25 GB download and needs 27.7 GB with headroom for about 8k tokens.
| Best quant | Default |
|---|---|
| Download size | 25 GB |
| Memory needed | 27.7 GB |
| Usable fast memory | 31.5 GB |
| Fit | fits in fast memory |
| Estimated speed | ~177 tok/s (estimate) |
| Command | ollama run nemotron-3.5-bolt:74b-a9b |
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