|
Three times ( VoiceClone | VoiceDesign | CustomVoice ) - Faster-Qwen3-TTS for NVIDIA DGX Spark (GB10)
|
|
63
|
4037
|
October 11, 2026
|
|
HOW-TO: setup-dgx-spark docker inference - A "Sane" Inference Stack for GB10 (Need Contributors!)
|
|
40
|
3695
|
October 10, 2026
|
|
Recipe: NOOA on DGX Spark (VSCode)
|
|
0
|
134
|
October 3, 2026
|
|
DeepSeek-V4-Flash on 2x DGX Spark throughput collapses at large prompt+concurrency. Would a 4x stack + Vision-Exp fix it?
|
|
0
|
187
|
September 23, 2026
|
|
ConnectX-7 bricked — stuck in pre-init / static_config_not_done after unsolicited mlnx-fw-updater firmware flash — ASUS GX10 [error -110]
|
|
25
|
1808
|
September 16, 2026
|
|
ConnectX-7 network cards disappear after DGX Spark system update due to cx7-pcie-hotplug driver issue
|
|
3
|
510
|
September 2, 2026
|
|
Qwen3.8-27B on single DGX Spark: 1.9x stock NVFP4 (2.5x FP8) at 16 concurrent, ~50 tok/s on a single request
|
|
7
|
1334
|
September 1, 2026
|
|
A Faster (maybe better?) Qwen 3.5 122B
|
|
9
|
1266
|
August 31, 2026
|
|
My DGX Spark extra cooling solution
|
|
15
|
7792
|
August 31, 2026
|
|
Qwen3.8-Flash-Next NVFP4 on 4x DGX Spark — vLLM TP4 serving, 4.7M-token KV pool, and the three fixes you WILL need
|
|
0
|
527
|
August 31, 2026
|
|
DGX Spark Cluster Dashboard
|
|
5
|
785
|
August 29, 2026
|
|
Single-Spark setups — which models do you actually run for coding, and how? (sharing mine + a test prompt)
|
|
60
|
10023
|
August 19, 2026
|
|
Running Kimi K3 on 24 DGX Spark Systems — TP24 vs TP8/PP3 Advice
|
|
39
|
4112
|
August 14, 2026
|
|
Deepseekv4 flash with QWEN for vision
|
|
2
|
789
|
August 12, 2026
|
|
Lowest KLD DeepSeek-V4-Flash-0731 on a single GB10 (drafter converted, 31 t/s on code), 256k context recipe
|
|
0
|
464
|
August 8, 2026
|
|
Sparkup - DGX Spark as code
|
|
0
|
341
|
August 5, 2026
|
|
Deepseek 4 0731 Single Spark - 40t/s decode - 131k ctx - Dwarfstar CUDA custom engine
|
|
3
|
712
|
August 5, 2026
|
|
1x DGX Spark: DeepSeek-V4-Flash-0731 on llama.cpp: 131K ctx/slot, 19.7 tok/s single-stream, 52 tok/s @ 4 concurrent
|
|
3
|
1133
|
August 5, 2026
|
|
Resetting a single GPU in a DGX node with gpu-operator running
|
|
2
|
204
|
August 4, 2026
|
|
6× DGX Spark, 200G RoCE fabric — My learning Journey
|
|
1
|
423
|
July 30, 2026
|
|
Best Daily Single Spark Driver - King Model - Still Qwen 3.5 122b?
|
|
15
|
2138
|
July 27, 2026
|
|
Super Idol Master: Multi-Agent Driven 3D Character Asset Pipeline on DGX Spark
|
|
0
|
361
|
July 22, 2026
|
|
My DGX Spark Hangs ... is this normal?
|
|
5
|
1159
|
July 15, 2026
|
|
Soft lockup in nvidia_modeset DisplayPort path during Xorg logout (DGX Spark, kernel 6.17.0-1018-nvidia)
|
|
3
|
374
|
July 2, 2026
|
|
Quick Test Results Regarding DGX SPARK Temperatures
|
|
2
|
1001
|
June 30, 2026
|
|
Docker Image: NVIDIA vLLM 0.23.0 with Claude Code 2.1.195+ Compatibility
|
|
6
|
597
|
June 29, 2026
|
|
2 node spark vs 3 or 4 node spark
|
|
18
|
2354
|
June 29, 2026
|
|
New model (one of the best i ever used, in my humble opinion): Qwen Agent World for local programming
|
|
0
|
717
|
June 29, 2026
|
|
Hybrid Edge-Cloud modular VLA(Vision Language Action) Pipeline using NVIDIA NIM for Autonomous Driving
|
|
0
|
139
|
June 28, 2026
|
|
Compute Sponsorship Proposal: Reasoning-Consistent VLA Framework for Autonomous Driving(DGX SPARK)
|
|
1
|
187
|
June 26, 2026
|