DeepSeek-v4-Flash-DSpark-2x-DGX-Spark
DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks
- 1.5k
- Python
- MIT
- 7 wk ago
MiaAI-Lab
Local AI, LLMs, tech thinker & builder
Built from MiaAI-Lab's public GitHub profile. Not on Take My Repo yet, so there are no posts or updates here.
DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks
Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)
Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux
GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold
DeepSeek-V4.1-Flash-1017 EXL3 on 2x DGX Sparks with TensorFold
Qwen3.8 Flash Next on one DGX Spark (TensorFold)
Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark
DeepSeek-V4.1-Flash on 3-4x NVIDIA DGX Sparks
DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks
Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards
GLM-5.3-Flash on DGX Sparks (ver 1104) with TensorFold
Claude Fable 5.2 HTML Files — 76 visual studies with screenshots and original prompts
Cap the GPU clock on NVIDIA DGX Sparks across all your machines, persistently
Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache
100 self-contained HTML pages made with Claude Opus 5.5 — gallery with screenshots and the exact prompts
2x DGX Spark recipe for LibertAIDAI/GLM-5.3-Flash-NVFP4 (NVFP4, Ray TP=2, multimodal)
GLM-5.3 EXL3 on DGX Sparks with TensorFold
DeepSeek-V4.1-Flash-1017 on 4 DGX Sparks with TensorFold, switchless support