Can RTX 3090 run Nemotron 3.5 Lightning 30B-A3B?

Q: Can RTX 3090 run Nemotron 3.5 Lightning 30B-A3B?

Yes. Measured 101.0 tok/s generation on RTX 3090, via llama.cpp CUDA b11804, Q4_K_M (23.7 GiB, partial CPU offload). Source: https://llm-benchmark.de/benchmark/run-20261024-084507-2c110a

Last updated: 31 Oct 2026

Yes. Measured 101.0 tok/s generation (llama.cpp CUDA b11804, Q4_K_M (23.7 GiB, partial CPU offload); source).

Every measured result for Nemotron 3.5 Lightning 30B-A3B on RTX 3090

Build	Quant / setup	Engine	tok/s
RTX 3090 + Ryzen 5 5600X + 32 GB DDR4: gpt-oss 20B at 211 tok/s, Qwen3.6 35B-A3B at 172, even gpt-oss 120B at 18 via NVMe paging (llm-benchmark.de)	Q4_K_M (23.7 GiB, partial CPU offload)	llama.cpp CUDA b11804	101.0	source

Memory: RTX 3090 has 24 GB. Nemotron 3.5 Lightning 30B-A3B weights are about 18.4 GB at Q4_K_M (30B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for Nemotron 3.5 Lightning 30B-A3B: best home rig for Nemotron 3.5 Lightning 30B-A3B.

Nemotron 3.5 Lightning 30B-A3B on other hardware: DGX Spark (GB10)

Other models measured on RTX 3090: DeepSeek R1 671B · Flint 40B-A2.5B · GLM 4.7 Flash · Gemma 4 31B · Nemotron 3.5 Bolt 74B-A9B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · gpt-oss 120B · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Nemotron 3.5 Lightning 30B-A3B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.