|
NVFP4 quantization of a 100B-class Llama on 2× DGX Spark — lessons + open questions
|
|
0
|
18
|
May 13, 2026
|
|
Fully custom CUDA-native Deepseek 4 Flash optimized for 1x Spark! antirez/ds4
|
|
20
|
893
|
May 13, 2026
|
|
Oops.. pressed the button for 2x GB10... no spousal approval, am I in trouble?
|
|
11
|
302
|
May 13, 2026
|
|
PyTorch CUDACachingAllocator NVML assertion when sharing CUDA context with llama.cpp on Orin Nano 8 GB (JetPack 6.2.2)
|
|
0
|
5
|
May 13, 2026
|
|
Introducing Tool Eval Bench CLI
|
|
116
|
2798
|
May 13, 2026
|
|
Eugr joins NVIDIA Spark Team!
|
|
102
|
2588
|
May 13, 2026
|
|
Request to enable Public API Endpoints for my personal organization
|
|
0
|
4
|
May 13, 2026
|
|
Rate Limit 40 -> 150
|
|
0
|
22
|
May 13, 2026
|
|
NVFP4 on DGX Spark / GB10 is broken. I bought 9 of these for this feature. Requesting NVIDIA's official roadmap and response
|
|
43
|
3826
|
May 12, 2026
|
|
Trouble with Llama 70b 3.3 Instruct FP8 Model at 3 tokens per second
|
|
15
|
522
|
May 12, 2026
|
|
My DGX Spark Setup (unsloth qwen36moe 2x, llama-cpp+mtp PR, ansible for easy mode)
|
|
1
|
199
|
May 12, 2026
|
|
Request for NVIDIA NIM API Rate Limit Increase (40 → 200 RPM)
|
|
0
|
16
|
May 12, 2026
|
|
Request for NVIDIA NIM API Rate Limit Increase (40 → 200 RPM) – Hermes Agent Multi-Model Development
|
|
0
|
21
|
May 12, 2026
|
|
DGX Spark stability / out of RAM / overheating
|
|
26
|
933
|
May 12, 2026
|
|
Spark-inference: Run 3 specialized models simultaneously on your DGX Spark — cybersecurity + coding + orchestration, 30-min setup
|
|
3
|
636
|
May 11, 2026
|
|
DeepSeek v4 Flash (IQ2XXS) on a single GB10!
|
|
2
|
1584
|
May 11, 2026
|
|
Manual Account Verification Request – Region: Uzbekistan (+998)
|
|
0
|
10
|
May 11, 2026
|
|
NVIDIA NIM API Rate Limit Increase Request (40 → 200 RPM) – Claude Code Multi-Agent Development
|
|
0
|
21
|
May 11, 2026
|
|
Qwen3.5 27B optimisation thread starting at 30+ t/s TP=1
|
|
23
|
2212
|
May 11, 2026
|
|
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8
|
|
2
|
372
|
May 9, 2026
|
|
Missing "Public API Endpoints" permission – 403 Forbidden on integrate.api.nvidia.com
|
|
0
|
22
|
May 9, 2026
|
|
Request to increase the API Rate Limit (40 -> 200)
|
|
0
|
21
|
May 9, 2026
|
|
DGX Spark Performance Degradation - GPU Power Draw Issue
|
|
50
|
2562
|
May 9, 2026
|
|
Request for NVIDIA NIM API Rate Limit Increase (40 → 200 RPM) – Agentic Coding Workflows
|
|
0
|
38
|
May 9, 2026
|
|
Request for NVIDIA NIM API Rate Limit Increase (40 → 200 RPM) – OpenClaw Agent Development
|
|
3
|
174
|
May 8, 2026
|
|
Request for Rate Limit Increase: 200 RPM for Multi-Agent Orchestration & Recursive Workflow (AIOC Project)
|
|
0
|
17
|
May 8, 2026
|
|
Request for Rate Limit Increate | Personal testing
|
|
1
|
46
|
May 7, 2026
|
|
NVIDIA NIM API Rate Limit Increase (40 → 200 RPM) – Personal Development & Multi-Agent Testing
|
|
0
|
55
|
May 7, 2026
|
|
Is Megatron training with Nemo/Megatron connector unsupported on GB10?
|
|
1
|
66
|
May 7, 2026
|
|
46tok/s with RedHatAI/gemma-4-26B-A4B-it-NVFP4
|
|
18
|
1297
|
May 6, 2026
|