Hi, I want to share the following.
This is the preview version.
Currently, I do not have two DGX Sparks and therefore, I am curious about your findings and results :-).
chrm
1
This looks very promising, hopefully it’s not just benchmaxxed. I would love to run this but they don’t have a quantization small enough for a 2x cluster. We’ll need one of our 4x guys to try this out until an autoround exists.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| DGX Spark performance | 49 | 6632 | February 13, 2026 | |
| DGX Spark PyTorch LLM training throughput up to 8x slower than expected | 2 | 713 | April 2, 2026 | |
| (Academic) GLM-5.2 on 2x DGX-Spark/GB10 nodes: Crazy 1-bit UD-IQ1_S + RPC llama.cpp + 256K context + 8 tok/s | 6 | 3163 | July 9, 2026 | |
| 6x Spark setup | 112 | 11297 | April 25, 2026 | |
| Now running 2x DGX Spark stacked over QSFP56 looking for model recs for agentic workloads (Hermes / OpenClaw) | 27 | 2934 | May 12, 2026 | |
| How are you planning on using your DGX spark? | 22 | 3409 | February 24, 2026 | |
| Fitting a high-quality REAP-less GLM-5.2 onto 4x DGX Spark | 0 | 1364 | June 29, 2026 | |
| DGX Spark + Qwen3-Next-80B: Proven Performance, But Missing Clear Path to NIM, TensorRT-LLM & Web UIs | 16 | 5067 | March 6, 2026 | |
| I am EXTREMely disappointed with the current state of DGX Spark | 91 | 21158 | June 24, 2026 | |
| Can someone please just help me set the DGX Spark up for optimal LLM use? | 11 | 1579 | June 20, 2026 |