Just an FYI for those those who track such things
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| MiniMax M2.7 TQ3 - A TurboQuant 3-bit quantized version of MiniMax-M2.7 for single DGX Spark | 6 | 3121 | June 12, 2026 | |
| Moving from Mac to NVIDIA: bought powerful hardware, but drowning in configs | 37 | 2745 | February 25, 2026 | |
| Some new development work for Qwen3 on the Spark | 5 | 827 | February 3, 2026 | |
| New bleeding-edge vLLM Docker Image: avarok/vllm-nvfp4-gb10-sm120 | 32 | 3203 | December 17, 2025 | |
| Tutorial: Build llama.cpp from source and run Qwen3 235B | 28 | 7744 | January 20, 2026 | |
| NVFP4 quantization of a 100B-class Llama on 2× DGX Spark — lessons + open questions | 5 | 382 | May 15, 2026 | |
| We unlocked NVFP4 on the DGX Spark: 20% faster than AWQ! | 144 | 8623 | March 14, 2026 | |
| FP8 Quantization Pipeline Issues with llmcompressor on NVIDIA vLLM Container (DGX Spark G10) | 0 | 38 | May 19, 2026 | |
| vLLM 0.17.0 MXFP4 Patches for DGX Spark: Qwen3.5-35B-A3B 70 tok/s, gpt-oss-120b 80 tok/s (TP=2) | 32 | 2513 | April 13, 2026 | |
| DGX Spark performance | 49 | 5851 | February 13, 2026 |