← CanIRunLocal · All hardware · All models
No. Nemotron 3.5 Lightning 30B-A3B (MoE) does not fit on RTX 3070 8GB: Q4_K_M needs 26.4 GB and 7.5 GB is usable.
Hardware: RTX 3070 8GB · Model: Nemotron 3.5 Lightning 30B-A3B (MoE)
RTX 3070 8GB has 8 GB of VRAM and 448 GB/s of memory bandwidth. RTX 3060 Ti 8GB has the same memory and bandwidth, so the fit numbers match; this page is RTX 3070 8GB. 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 7.5 GB. Partial offload may also use 60% of that system RAM. Nemotron 3.5 Lightning 30B-A3B (MoE) (31.6B, 3B active, NVIDIA) at Q4_K_M is a 25 GB download and needs 26.4 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 25 GB |
| Memory needed | 26.4 GB |
| Usable fast memory | 7.5 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run nemotron-3.5-lightning:30b-a3b-q4_K_M |
Smallest hardware that runs it: RTX 3090 24GB at Q4_K_M (partial offload (slower), 26.4 GB needed, 23.5 GB usable, about 49 tok/s (estimate)). Can a RTX 3090 24GB run Nemotron 3.5 Lightning 30B-A3B (MoE)?
A smaller NVIDIA model that fits this hardware: Nemotron Labs Dory 1.0 4B at Q5_K_M (fits in fast memory, 4.5 GB). Can a RTX 3070 8GB run Nemotron Labs Dory 1.0 4B?
Open RTX 3070 8GB 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