NVIDIA-Nemotron-3.5-Super-VL-120B-A12B
1recorded run
48.0best tok/s
1verified
What the NVIDIA-Nemotron-3.5-Super-VL-120B-A12B numbers mean
The fastest verified result on our board is 48.0 output tok/s on an DGX Spark at NVFP4 with a 262144-token context. That is about 20.8 ms per generated token — 500 tokens takes roughly 10.4 seconds.
How much VRAM does NVIDIA-Nemotron-3.5-Super-VL-120B-A12B need?
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B has 120.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.
| Quantisation | Estimated VRAM | Smallest card that fits |
|---|---|---|
| Q4_K_M (4-bit) | 78.4 GB | 96 GB |
| Q8_0 (8-bit) | 147.4 GB | 192 GB |
| FP16 (16-bit) | 276.8 GB | multi-GPU or CPU offload |
Fastest GPUs for this model (best tok/s)
- DGX Spark48.0
Models with a similar footprint
| Model | Params | Q4_K_M weights |
|---|---|---|
| Laguna-S-2.1 | 118B | 66.4 GB |
| gpt-oss-120b | 117B | 65.8 GB |
| Qwen 3.8 Flash | 125B | 70.3 GB |
| Qwen 3.8 Flash-Next Base | 125B | 70.3 GB |
| Ling-3.0-flash | 127B | 71.4 GB |
| Llama-4-Scout-17B-16E-Instruct | 109B | 61.3 GB |