What does it do?
It serves the DeepSeek-V4.1-Flash-1017 model from two NVIDIA DGX Sparks through an OpenAI-compatible API, so clients can use the standard OpenAI API format. [1] It supports a 1,048,576-token context window, image input, tool calling, and thinking on or off, using TensorFold's native Zig engine and 2.9-bit EXL3 quantization. [2] DSpark speculative decoding uses the checkpoint's own draft blocks to propose tokens. [3]
Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
README badges
Embed a badge in your README or website.
