Topics tagged deepseek

Topic	Replies	Views	Activity
DeepSeek-V4.1-Flash-1017 (EXL3 2.9bpw) on 2x DGX Spark with TensorFold: 57 tok/s text, 92 tok/s code, 2.1-2.3x the vLLM kit DGX Spark / GB10 deepseek	354	12422	November 2, 2026
New Deepseek 4.1 flash recipe DGX Spark / GB10 deepseek	135	9078	November 2, 2026
So for Dual Spark what is the Choice now: GLM5.3 Flash or Deepseek v4 Flash DGX Spark / GB10 deepseek	111	9369	November 2, 2026
DeepSeek-V4-Flash on 2x DGX Spark throughput collapses at large prompt+concurrency. Would a 4x stack + Vision-Exp fix it? DGX Spark / GB10 Projects cuda , inference-fil-spark , deepseek , dgx , dgx-station , dgx-spark-issue	1	302	November 1, 2026
Native Rust + CUDA engine for DeepSeek-V4.1-Flash on 4x Sparks (132 tok/s, 25s boot, 1M context) DGX Spark / GB10 cuda , deepseek	11	839	November 1, 2026
Introducing veloGB10 a new inference engine ( Qwen3.6-27b-nvfp4 ~50 tok/s on 2x cluster and ~40+ tok/s on single, and more) DGX Spark / GB10 Projects cuda , kernel , deepseek	14	1709	November 1, 2026
DeepSeek V4.1 Flash on 8× DGX Spark: TP8/EP8 concurrency results DGX Spark / GB10 deepseek	5	359	November 1, 2026
Where's DeepSeek-V4.1-Flash-1017? — Follow-up on NIM Onboarding Models nim , deepseek	0	34	November 1, 2026
DeepSeek-V4-Flash-Vision-Exp on one DGX Spark: text + images, 245k context, CUDA graphs — plus a pack that keeps 90 % of the original model DGX Spark / GB10 deepseek	18	2079	November 1, 2026
Request access to third-party models on NIM free tier (404 "Function not found for account") Access/Accounts nim , granite-34b-code-instruct , codellama-70b , mistral-large , deepseek , nemotron	0	33	October 31, 2026
Let’s optimize DeepSeek-V4.1-Flash-1017 for 2× DGX Spark DGX Spark / GB10 cuda , llama , deepseek	5	1105	October 31, 2026
Manual Account Verification Request — Country Code Missing (+7) Access/Accounts deepseek	0	23	October 31, 2026
NVIDIA API: Models Endpoint Works, but Chat Completions Time Out Models deepseek	0	84	October 30, 2026
Request to enable "Public API Endpoints" for my personal account (404 Function not found) Access/Accounts nim , deepseek	0	11	October 30, 2026
Flare - NVIDIA's new inference server in Rust DGX Spark / GB10 gaming , deepseek	29	3540	October 30, 2026
403 Authorization Failed on NVIDIA NIM API — /v1/models works but /v1/chat/completions fails Models nim , deepseek	0	43	October 30, 2026
Welcome Athena Logos & Engine: The new AI assistant that lives on your DGX Spark DGX Spark / GB10 deepseek	4	594	October 30, 2026
Permission for my organization Access/Accounts deepseek	0	27	October 30, 2026
Deepseek V4.1 Flash Issues: Models deepseek	1	450	October 29, 2026
Keep GLM 5.3! Models deepseek	7	712	October 29, 2026
Deepseek-V4.1-flash + glm-5.3-flash extreme loss of speed Models nim , deepseek	3	300	October 29, 2026
POST /v1/chat/completions times out with 0 bytes received while GET /v1/models returns 200 — Public API Endpoints entitlement verification requested Access/Accounts nim , deepseek	0	56	October 29, 2026
How can i acess the deepseek v4 pro for free Access/Accounts ai , deepseek	0	47	October 29, 2026
Deepseek-V4.1-Flash-1017 Models nim , deepseek	1	294	October 28, 2026
Unable to Access DeepSeek V4.1 Flash and Kimi Models Through NVIDIA NIM API Access/Accounts nim , deepseek	0	85	October 28, 2026
Api error Access/Accounts deepseek	0	56	October 28, 2026
Sharing GB10s with a dev team DGX Spark / GB10 deepseek , nemotron	11	639	October 27, 2026
DeepSeek V4.1 Flash API Extremely Slow – 3–5+ Minutes for Simple Responses Access/Accounts deepseek	2	523	October 27, 2026
Request to enable "Public API Endpoints" permission for Personal organization (403 Authorization failed) Access/Accounts nim , deepseek , nemotron	0	34	October 27, 2026
GIGABYTE AI TOP ATOM: stopped fan, severe heat and loss of access after updates DGX Spark / GB10 deepseek	3	247	October 27, 2026