DGX Spark Local Inference Toolkit: llama.cpp, Vibe-Coding setup, and Whisper TUI.
-
Updated
Feb 14, 2026 - HTML
#
nvidia-dgx-spark
Here are 5 public repositories matching this topic...
3-bit Lloyd-Max KV Cache Compression for LLM Inference on NVIDIA DGX Spark GB10 — 5.12x compression, 0.983 cosine similarity, pure numpy on ARM unified memory
compression numpy transformers quantization lloyd-max kv-cache unified-memory vllm llm-inference vibe-coding claude-code gb10 nvidia-dgx-spark arm-aarch64
-
Updated
Apr 3, 2026 - Python
Deploy Nemotron 3 Nano 30B on NVIDIA DGX Spark using TensorRT-LLM (Blackwell GB10, NVFP4 quantization, OpenAI-compatible API)
docker inference aarch64 mamba mixture-of-experts blackwell local-llm tensorrt-llm nemotron openai-compatible nvfp4 nvidia-dgx-spark
-
Updated
Mar 22, 2026 - Shell
Local-first developer dashboard for the NVIDIA DGX Spark.
python typescript nextjs artificial-intelligence nvidia fastapi huggingface nvidia-nemo agentic-ai nvidia-dgx-spark
-
Updated
Apr 17, 2026 - TypeScript
Deploy Nemotron 3 Nano 30B with 1M context window on NVIDIA DGX Spark using llama.cpp (Blackwell sm_121, Q4_0 KV cache quantization)
cuda inference aarch64 mamba mixture-of-experts blackwell long-context llama-cpp local-llm gguf kv-cache-quantization nemotron nvidia-dgx-spark 1m-context-window
-
Updated
Mar 22, 2026 - Shell
Improve this page
Add a description, image, and links to the nvidia-dgx-spark topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nvidia-dgx-spark topic, visit your repo's landing page and select "manage topics."