Models › Nemotron 3 Super 120B-A12B
Nemotron 3 Super 120B-A12B: VRAM needs and speed by GPU
We have 1 measured speed results for it.
120.67B parameters (mixture-of-experts, ~12.1B active) · GGUF files on Hugging Face
Measured speeds
| Hardware | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| NVIDIA DGX Spark (GB10) | 19.9 | 769 | Q4_K | CUDA FA on | tg32 | llama.cpp benches details |
Memory needed per quantization
| Quant | File size | Needs (estimate) | Smallest card it fits |
|---|---|---|---|
| Q4_K | 69.9 GB | 72.9 GB | 96 GB cards |
Expected speed on popular hardware
| Hardware | Best quant that fits | Expected tok/s |
|---|---|---|
| NVIDIA RTX 3060 | Does not fit | |
| NVIDIA RTX 4060 Ti | Does not fit | |
| NVIDIA RTX 3090 | Does not fit | |
| NVIDIA RTX 4090 | Does not fit | |
| NVIDIA RTX 5090 | Does not fit | |
| AMD Radeon RX 7900 XTX | Does not fit | |
| Apple M4 Pro (20-core GPU) | Does not fit | |
| Apple M3 Max (40-core GPU) | Does not fit | |
| AMD Ryzen AI Max+ 395 (Radeon 8060S) | Q4_K | 14.9 estimate |
Too big for your card?
Run Nemotron 3 Super 120B-A12B on a rented 24-80 GB GPU by the hour.
Rent a bigger GPU on RunPodAffiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.