Topics tagged deepseek
deepseek Topic Replies Views Activity DeepSeek-V4.1-Flash on 4x DGX Spark GB10 (CX7 ring): full setup + cold prefill & decode numbers up to 1M context DGX Spark / GB10 Projects deepseek 15 360 November 19, 2026 咨询ORIN NANO 8G支持的LLM模型 Jetson Orin Nano llm , deepseek 3 28 November 19, 2026 New Deepseek 4.1 flash recipe DGX Spark / GB10 deepseek 168 13341 November 19, 2026 Seeking 1x DGX Spark / GB10 tester: zero-Electron Python AI workstation (Local vLLM / NVIDIA Flare / NIM) + unified-memory [N/A] telemetry fix DGX Spark / GB10 nim , llm , deepseek 0 46 November 19, 2026 Four Sparks vs Two.
Looking for TP=4 vs TP=2 experiences DGX Spark / GB10 performance , benchmarks , llm , deepseek 19 354 November 19, 2026 Flare - NVIDIA's new inference server in Rust DGX Spark / GB10 gaming , deepseek 34 4850 November 18, 2026 Where's DeepSeek-V4.1-Flash-1017? — Follow-up on NIM Onboarding Models nim , deepseek 20 1034 November 18, 2026 Request to Enable Public API Endpoints for All Free Catalog Models (404 Function Not Found) Access/Accounts nim , deepseek , nemotron 1 27 November 18, 2026 Deepseek V4.1 Flash Deprecated Models nim , deepseek 7 631 November 18, 2026 So for Dual Spark what is the Choice now: GLM5.3 Flash or Deepseek v4 Flash DGX Spark / GB10 deepseek 122 10835 November 18, 2026 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 391 18313 November 18, 2026 DeepSeek-V4.1-Flash on 4x GB10: 262K cold input in 27.3s, open-source runtime DGX Spark / GB10 Projects deepseek 8 263 November 17, 2026 Nim is suck now Models nim , deepseek 1 135 November 17, 2026 Deepseek Flash V4.1 Deprecated Access/Accounts nim , deepseek 0 52 November 17, 2026 Let's optimize ...
DGX Spark DGX Spark / GB10 ota , jetson , agentic-ai , deepseek 18 2552 November 16, 2026 Chat/completions hangs for deepseek-v4.1-flash and glm-5.3-flash, GET /v1/models works Access/Accounts nim , deepseek 1 169 November 16, 2026 DeepSeek-V4-Flash, GLM-5.3-Flash, Qwen3.8-Flash-Next DGX Spark / GB10 deepseek 35 4923 November 16, 2026 Request to enable Public API Endpoints – 404 Function Not Found for account (deepseek-v4.1-flash hangs) Access/Accounts nim , mistral-large , llama , deepseek , nemotron 0 31 November 16, 2026 Hermes is losing its glory, what is next?
DGX Spark / GB10 Projects deepseek 111 8680 November 15, 2026 Request to enable "Public API Endpoints" permission for my personal organization Access/Accounts nim , deepseek 0 33 November 15, 2026 [Release / PoC] DeepSeek-V4.1-Flash-1017 (All 384 Experts) in 45.8 GB / 58.5 GB RAM on 1x 128 GB GB10 — Free Binary, Instant Access DGX Spark / GB10 Projects deepseek 1 461 November 14, 2026 [Open Source] Flash1017-Engine + Theoretical Blueprint to fit ALL 384 Experts of DeepSeek-V4.1-Flash-1017 (748B) in 106 GB RAM on a single 128 GB GB10 DGX Spark / GB10 Projects llama , deepseek , rust 20 1572 November 14, 2026 DeepSeek V4.1 Flash stalls in Playground and API, Kimi K2.6 returns 404 Access/Accounts nim , deepseek 0 74 November 13, 2026 Request activation of "Public API Endpoints" permission for personal account Access/Accounts deepseek 0 19 November 13, 2026 Chat/completions hangs with 0 bytes for deepseek-v4.1-flash and gpt-oss-20b, but nemotron-3.5-super-vl works Access/Accounts deepseek , nemotron 1 70 November 13, 2026 Qwen3.8-Flash-Next, GLM-5.3-Flash, DeepSeek-V4-Flash on 2x DGX Spark - prefill, TTFT, SWE-bench Pro DGX Spark / GB10 deepseek 3 1600 November 13, 2026 Welcome Athena Logos & Engine: The new AI assistant that lives on your DGX Spark DGX Spark / GB10 deepseek 7 985 November 13, 2026 GLM-5.3-Flash and DeepSeek 504 errors; same-key Nemotron works Access/Accounts nim , deepseek , nemotron 0 75 November 13, 2026 Models not working Access/Accounts deepseek , nemotron 0 78 November 12, 2026 Request for NVIDIA Build API Rate Limit Increase (40 → 200 RPM, Self-Evolving Research Platform) Access/Accounts nim , llama , deepseek , nemotron 0 39 November 12, 2026 next page →