Topics tagged llama

Topic	Replies	Views	Activity
Request API key public access, getting http error 404 NVAPI llama , nemotron	0	9	October 7, 2026
Request to enable Public API endpoints for personal organization Access/Accounts llama , nemotron	0	9	October 6, 2026
Aleph Alpha Kolibri-1 - interesting new model for german and english texts DGX Spark / GB10 llama	8	472	October 5, 2026
Request: Enable "Public API Endpoints" permission for personal account Access/Accounts api , nim , llama , deepseek , nemotron	0	17	October 5, 2026
Single Spark Qwen3.8 Flash-Next + Qwen3.8 27B Left/Right Brain Hermes MoA (35-39 toks/s) DGX Spark / GB10 Projects llama , agentic-ai , deepseek	23	2261	October 4, 2026
Kolibri-1 (Aleph Alpha's 78B FP8 MoE) runs on the Spark – setup, numbers, and a few things I'd love to share DGX Spark / GB10 llama	6	409	October 4, 2026
Request to enable the "Public API endpoints" for personal organization Access/Accounts nim , llama , deepseek , nemotron	0	19	October 3, 2026
Introducing Tool Eval Bench CLI DGX Spark / GB10 Projects llama , agentic-ai	212	10231	October 3, 2026
New tool: llama-benchy - llama-bench style benchmarking for ANY LLM backend (vLLM, SGLang, llama.cpp, etc.) DGX Spark / GB10 Projects llama	18	4425	October 3, 2026
Yet another monitoring dashboard for GB10 clusters or even standalone installs DGX Spark / GB10 Projects llama	11	1047	October 2, 2026
Nemotron 3 Nano on one RTX 5090 with NIM: ~300 tok/s, flat to 120k context, 128 concurrent requests NVIDIA Nemotron inception , nim , llama , nemotron	1	67	October 2, 2026
Request to enable Public API Endpoints for my personal account Access/Accounts mistral-7b-instruct-v03 , llama , nemotron	0	20	October 1, 2026
NIM vs Ollama on RTX 5090: 7.3x Faster Inference + NeMo Guardrails at 2.1% Overhead — 870 Data Points NIM on RTX AI PCs and Workstations cuda , benchmarks , inception , rtx , nim , llama , nemo-guardrails	1	754	October 1, 2026
Why NIM? Llama 3.1 8B on one RTX 5090, from 1 to 128 concurrent requests NIM on RTX AI PCs and Workstations inception , rtx , nim , llama-31-8b-instruct , llama	0	33	October 1, 2026
Request to enable "Public API Endpoints" permission for my personal organization Access/Accounts access-control , nim , llama-31-8b-instruct , llama	0	19	October 1, 2026
DGX Spark (GB10): cuDevicePrimaryCtxRetain returns CUDA_ERROR_OUT_OF_MEMORY intermittently with 67-74 GiB available DGX Spark / GB10 nim , llama , nemotron , dgx-spark-issue	1	114	September 30, 2026
RTX 5060 Ti (SM120): GPU engine hang / device loss under sustained low-precision tensor-core workloads — reproducible in ~2.5 minutes Linux cuda , driver , cublas , llama , bug , windows	0	40	September 30, 2026
Ollama not supporting jetson? Jetson Orin Nano llama	15	211	September 30, 2026
403 Authorization Failed — /v1/chat/completions while /v1/models returns 200 Access/Accounts llama , nemotron	0	22	September 30, 2026
Requesting "Public API Endpoints" permission for Account 9WQBAF9cBB8vtLjT0KwYA0XZy_Em9lImFTx5y7PNSM0 Access/Accounts nim , llama , nemotron	0	25	September 29, 2026
Three RTX 5060 Ti (GB206) randomly fallen off the bus (Xid 79/154) at any load level, no PCIe/AER precursor — open kernel module 595.99.02 Linux llama	4	113	September 29, 2026
GLM-5.3-Flash (NVFP4+DFlash2) on 2x Spark: does not scale with concurrency - anyone else seeing this? DGX Spark / GB10 llama , deepseek	4	373	September 28, 2026
RTX PRO 5000 Blackwell (Windows): displays freeze for the whole duration of GPU-saturating work - only after ~24h+ uptime, fresh boot immune, only reb Drivers - Linux, Windows, MacOS llama	4	295	September 27, 2026
403 Authorization failed — Public API Endpoints access for my personal account Access/Accounts llama , deepseek , nemotron	0	24	September 27, 2026
Title: New Free Developer Account Getting 403/HTML Page Redirects on NIM Chat Completions NVIDIA AI Workbench nim , llama	0	21	September 26, 2026
Request: Enable "Public API Endpoints" for Personal Account — 404 on /v1/chat/completions Access/Accounts api , access-control , nim , llama-31-8b-instruct , llama , deepseek	0	25	September 26, 2026
RTX PRO 4500 Blackwell – repeated TDR (117/141/1B8) and “GPU is lost” during LLM/CUDA workloads on Windows 11 Drivers - Linux, Windows, MacOS cublas , gaming , llama	0	56	September 26, 2026
Full Kimi K3 running on 16x GB10 cluster DGX Spark / GB10 Projects llama	146	11327	September 25, 2026
Request to enable "Public API Endpoints" for my personal organization Access/Accounts nim , gemma-2-9b-it , llama , nemotron	0	31	September 25, 2026
Stuck on Phone Verification: Missing Pakistan (+92) Country Code for NVIDIA NIM API Access Access/Accounts nim , llama , nemotron	0	22	September 24, 2026