Configs › Nemotron-3.5-Super-VL-120B-A12B on DGX Spark: 28 tok/s measured
Nemotron-3.5-Super-VL-120B-A12B on DGX Spark: 28 tok/s measured
Measured Nemotron-3.5-Super-VL-120B-A12B speeds: 28 tok/s on DGX Spark. 1 config, each linked to its source, snapshot 2026-10-29.
Snapshot 2026-10-29 · 413 configs on AI boxes and 288 on GPU cards · 121 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Fastest measured single-stream run of Nemotron-3.5-Super-VL-120B-A12B: 28 tok/s on DGX Spark (NVFP4, atlas (speculative decode, dflash-8)), snapshot 2026-10-29.
Fastest measured run on each box
| Hardware | Decode tok/s | Quant | Backend | Context | Trust | Configs on this box | Source |
|---|---|---|---|---|---|---|---|
| DGX Spark | 28 | NVFP4 | atlas (speculative decode, dflash-8) | Extracted, source-linked | 1 | source |
Questions and answers
- How fast is Nemotron-3.5-Super-VL-120B-A12B on local hardware?
- The fastest measured single-stream run is 28 tok/s on DGX Spark (NVFP4, atlas (speculative decode, dflash-8)). TokenMark tracks 1 single-stream config for Nemotron-3.5-Super-VL-120B-A12B on 1 box.
- How many measured configs does TokenMark have for Nemotron-3.5-Super-VL-120B-A12B?
- 1 single-stream config on 1 box, newest source check 2026-10-16. Every row links to where it was measured.
All measured configs for Nemotron-3.5-Super-VL-120B-A12B
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Nemotron-3.5-Super-VL-120B-A12B | DGX Spark | NVFP4 | atlas (speculative decode, dflash-8) | 28 tok/s | Extracted, source-linked | source |
Last updated: snapshot 2026-10-29; newest source check 2026-10-16. Rankings use single-stream runs only; aggregate and multi-GPU rows are kept off them.
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.