Topics tagged llama

Topic	Replies	Views	Activity
GLM-5.2-Int4-Int8 on 8× GB10: ~1,200 t/s prefill, 33–54 t/s avg decode (generic - coding/structured) DGX Spark / GB10 gaming , llama	27	1800	July 30, 2026
Laguna S 2.1 Config & Benchmarks DGX Spark / GB10 llama	58	7203	July 29, 2026
Request to enable Public API Endpoints for my account — 404 Function not found Access/Accounts nim , llama , deepseek , nemotron	0	32	July 29, 2026
Nemoguard-8b-topic-control NIM returns HTTP 500 (TensorRT-LLM CUDA illegal memory access) — reproducible Models nim , llama	0	41	July 28, 2026
Request to enable "Public API Endpoints" permission for my personal organization Access/Accounts nim , llama-31-8b-instruct , llama	0	20	July 28, 2026
Manual Account Verification Request Access/Accounts nim , llama , deepseek	0	26	July 26, 2026
SIPA OS fine tuning experiment Android Development cuda , llama , deepseek	0	28	July 26, 2026
Models That Don't Work Models nim , codestral-22b-instruct-v01 , nemotron-4-340b-reward , llama , deepseek , nemotron	0	124	July 25, 2026
Running Speech-to-Speech with Qwen3-TTS on NVIDIA GB10 (DGX Spark): Bypassing GGML CUDA Crashes DGX Spark / GB10 llama	2	256	July 24, 2026
Solar Open2 250B (NVFP4) on a 2× GB10 pair — FP8 KV cache A/B on a hybrid linear-attention MoE DGX Spark / GB10 llama	0	250	July 24, 2026
Rate Limit Increase Request: Benchmarking Novel Grounding Framework on Small Language Models Models llama , nemotron	2	76	July 24, 2026
Request to enable "Public API Endpoints" for my account — moonshotai/kimi-k2.6 returns 404 Function not found Access/Accounts jetson , llama-31-8b-instruct , llama , nemotron	0	116	July 24, 2026
Function not found for account — kimi-k2.6 and minimax-m3 return 404 on Free Endpoints Access/Accounts llama	0	86	July 24, 2026
Public API Endpoints scope missing on personal org — Llama/Gemma work, Kimi/DeepSeek/Qwen/Nemotron all 404 Access/Accounts nim , llama-31-8b-instruct , llama-31-70b-instruct , llama , deepseek , nemotron	0	50	July 24, 2026
Request to enable "Public API Endpoints" permission for my personal organization Access/Accounts llama	0	25	July 24, 2026
Account Activation Request - No API Key Permissions Access/Accounts llama , deepseek	0	24	July 24, 2026
Eugr joins NVIDIA Spark Team! DGX Spark / GB10 llama	109	4892	July 23, 2026
Request to enable "Public API Endpoints" permission — personal org (Belgium) Access/Accounts nim , mistral-large , llama-31-8b-instruct , llama-31-70b-instruct , llama , deepseek	0	52	July 22, 2026
Nemotron 3 Super (nemotron-3-super-120b-a12b) returning 429 continuously for 3+ days, new API key didn't help Access/Accounts llama-31-8b-instruct , llama , nemotron	0	60	July 21, 2026
MiniMax-M3-AWQ on 4× GB10, fp8 KV, 262k context, adaptive reasoning, ~30 tok/s DGX Spark / GB10 llama	17	1235	July 21, 2026
Three times ( VoiceClone \| VoiceDesign \| CustomVoice ) - Faster-Qwen3-TTS for NVIDIA DGX Spark (GB10) DGX Spark / GB10 Projects docker , spark , llm , speech , llama , dgx	56	2733	July 21, 2026
Request to enable "Public API Endpoints" for my account - kimi-k2.6 returns 404 Function not found Access/Accounts llama , deepseek	0	120	July 21, 2026
Jetson Agent Skills : AI-Assisted Workflows for Device & BSP Customization Jetson Thor jetson , llama , agentic-ai , nemoclaw , openclaw	1	236	July 21, 2026
Credit & rate-limit increase request (1,000 → 5,000 credits, 40 → 200 RPM) Access/Accounts api , nim , llama , nemotron	1	53	July 20, 2026
sparkDash - Multi-unit monitoring dashboard for NVIDIA DGX Spark DGX Spark / GB10 llama	0	322	July 20, 2026
Three node Spark clusters (without a switch) are now supported in spark-vllm-docker and sparkrun! DGX Spark / GB10 llama	15	2777	July 19, 2026
DeepSeekv4 Flash for 1x Spark [REAP25] [PrismaAURA] DGX Spark / GB10 Projects llama , agentic-ai , deepseek	3	822	July 19, 2026
How three.ws Translates a Web App into 100+ Languages with NVIDIA NIM: an LLM-Powered i18n Pipeline Models ai-training , nim , llama , nemotron	0	65	July 19, 2026
Request for NVIDIA Build API Rate Limit Increase (40 RPM → 200 RPM) Access/Accounts nim , llama-31-8b-instruct , llama	0	30	July 18, 2026
cuBLASLt sm_120 (Blackwell): TF32 split-K nvjet kernel raises "Warp Barrier Arrival Mismatch" — intermittent illegal access / GPU hang (RTX 5090) GPU-Accelerated Libraries cublas , llama	2	174	July 17, 2026