Has anyone tried running this model on 2x sparks? Curious if you have any metrics or feedback?
Thanks!
Devstral-2-123B-NVFP4-TensorRT-LLM
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| TRT LLM for Inference - two Sparks example is VERY slow | 5 | 817 | October 23, 2025 | |
| vLLM to run Devstral 2 for Spark? | 1 | 509 | January 27, 2026 | |
| Value of 2nd Spark? | 21 | 2712 | March 30, 2026 | |
| The best 2x spark qwen 3.6 27b recipe | 8 | 628 | July 6, 2026 | |
| DGX Spark performance | 49 | 6361 | February 13, 2026 | |
| NVIDIA folks -- where is this promised nvfp4 speedup? | 27 | 2916 | March 26, 2026 | |
| DGX Spark Playbook Request - BF16 -> nvFP4 via model distillation | 2 | 285 | May 4, 2026 | |
| TensorRT-LLM + nvidia/Llama-3.3-70B-Instruct-NVFP4 = 5 tok/s | 3 | 723 | January 18, 2026 | |
| Now running 2x DGX Spark stacked over QSFP56 looking for model recs for agentic workloads (Hermes / OpenClaw) | 27 | 2704 | May 12, 2026 | |
| Can someone please just help me set the DGX Spark up for optimal LLM use? | 11 | 1254 | June 20, 2026 |