ahtx / kindi
Kindi 0.4: local LLM inference on low-cost NVIDIA GPUs, Radeon 780M and CPUs. Bonsai 2B-27B, AH-Nanbeige4.3-33B and experimental Nemotron, with an OpenAI-compatible server.
Why this job: says: local llm, llm inference; topics: local-llm, llm-inference
Get started
curl -fsSL https://amirhusain.com/kindi/install.sh | bash - Maintenance
- Active
- Last commit 4 days ago
- Stars
- 148
- +33 this week
- Licence
- AGPL-3.0
- Share-alike, even hosted
- Downloads for
- None listed
- No release files
- Latest version
- v0.4.0
- Released 4 days ago
- Built with
- Python
- 51% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 40% closed
- 15 still open
- Pull requests
- 0 merged
- 1 waiting
- Releases
- 4
- 4 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| LMCache / LMCache | 12,310 | today | Apache-2.0 | Linux |
| SemiAnalysisAI / InferenceX | 2,010 | today | Apache-2.0 | No downloads |
| mw00 / project-maya | 2,712 | 2 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 51%
- Cuda 39%
- C 5%
- Shell 5%
Topics
- bitnet
- cuda
- kepler
- llm-inference
- local-llm
- openai-compatible
- quadro
- ternary
- ampere
- maxwell
- pascal
- tensor-parallelism
Project record
- JobLocal LLMs
- StatusNew to our list
- Commits12
- Forks35
- Watching5
- CreatedOct 20, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026