Can RTX 3090 run Nemotron 3.5 Bolt 74B-A9B?
Probably only partly: the weights are larger than its memory, so part of the model likely ran from system RAM. Measured 87.75 tok/s generation with part of the model offloaded to system RAM (llama.cpp build 11669 (620d2225), NVIDIA mixed 2-bit IQ2 GGUF (22.0 GB); source).
Every measured result for Nemotron 3.5 Bolt 74B-A9B on RTX 3090
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| RTX 3090 running Nemotron 3.5 Bolt 74B-A9B in 24 GB (IQ2) | NVIDIA mixed 2-bit IQ2 GGUF (22.0 GB) | llama.cpp build 11669 (620d2225) | 87.75 CPU offload | source |
Memory: RTX 3090 has 24 GB. Nemotron 3.5 Bolt 74B-A9B weights are about 45.3 GB at Q4_K_M (74.04B 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 Bolt 74B-A9B: best home rig for Nemotron 3.5 Bolt 74B-A9B.
Nemotron 3.5 Bolt 74B-A9B on other hardware: DGX Spark (GB10) · RTX 4090 · RTX 5090
Other models measured on RTX 3090: DeepSeek R1 671B · Flint 40B-A2.5B · GLM 4.7 Flash · Gemma 4 31B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · gpt-oss 20B
Not enough VRAM? Rent before you buy. Run Nemotron 3.5 Bolt 74B-A9B 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.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.