prabanta-dev / janas
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
Why this job: says: llama.cpp; topics: local-llm, gguf, inference-engine, quantization
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 685
- +86 this week
- Licence
- GPL-3.0
- Share-alike terms
- Downloads for
- 2 systems
- Windows, Linux
- Latest version
- v2026.11.10
- Released today
- Built with
- C
- 98% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 62% closed
- 18 still open
- Pull requests
- 0 merged
- 9 waiting
- Releases
- 22
- 22 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 |
|---|---|---|---|---|
| carloslfu / slotstream | 662 | yesterday | MIT | No downloads |
| mw00 / project-maya | 2,741 | yesterday | MIT | No downloads |
| simplexai-labs / PolyStrata | 956 | 3 days ago | MIT | Windows |
More: download files, languages, topics and project record
Download files, v2026.11.10
- Windows4 files, 9 downloads
- Linux4 files, 7 downloads
Languages
- C 98%
- FreeBASIC 1%
- Shell <1%
- HTML <1%
Topics
- avx2
- c
- cpu-inference
- gguf
- inference-engine
- linux
- llm
- local-llm
- mixture-of-experts
- moe
- nvme
- quantization
Project record
- JobLocal LLMs
- StatusListed
- Commits100
- Forks71
- Watching8
- Stars in 28 days+236
- CreatedSep 20, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026