Picom-code / pico-dgx-ds4
DeepSeek V4.1 Flash on 4x DGX Spark: 90/144 tok/s chat/code single-user, 376 tok/s at 16 distinct users, 1M context, images. Fork of blaesus/dsgx10.
Why this job: topics: local-llm, llm-inference, inference-engine
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 days ago
- Stars
- 107
- +84 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Cuda
- 42% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 0% closed
- 5 still open
- Pull requests
- 0 merged
- 12 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| simplexai-labs / PolyStrata | 1,029 | yesterday | MIT | Windows |
| Avarok-Cybersecurity / atlas | 717 | 52 days ago | AGPL-3.0 | No downloads |
| raullenchai / twinspark | 176 | 3 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Cuda 42%
- Python 27%
- C++ 18%
- Rust 9%
Topics
- cuda
- deepseek
- dgx-spark
- inference-engine
- llm-inference
- local-llm
- multi-node
- openai-api
- rdma
- roce
Project record
- JobLocal LLMs
- StatusNew to our list
- Commits65
- Forks18
- Watching2
- CreatedNov 5, 2026
- First seen by usNov 14, 2026
- CheckedNov 14, 2026