FareedKhan-dev / kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Why this job: topics: llm-inference, inference-engine, quantization
Get started
python3 tools/sim_cache.py tests/fixtures/expert_trace.bin - Maintenance
- Active
- Last commit 40 days ago
- Stars
- 11,657
- +161 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.1.0
- Released 40 days ago
- Built with
- C
- 71% of the code
Is it looked after?
- Contributors
- 6
- Last 90 days
- Issues
- 89% closed
- 2 still open
- Pull requests
- 22 merged
- 26 waiting
- Releases
- 3
- 3 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| prabanta-dev / janas | 691 | yesterday | GPL-3.0 | Windows, Linux |
| brontoguana / krasis | 528 | 3 days ago | Custom | Windows, Linux |
| EfficientMoE / MoE-Infinity | 382 | 4 days ago | Apache-2.0 | Linux |
More: languages, topics and project record
Languages
- C 71%
- Python 20%
- Shell 4%
- Makefile 2%
Topics
- avx2
- c99
- cpu-inference
- deep-learning
- from-scratch
- inference-engine
- kimi-k3
- linear-attention
- llm
- llm-inference
- machine-learning
- memory-efficient
Project record
- JobLocal LLMs
- StatusListed
- Commits98
- Forks1,808
- Watching100
- Stars in 28 days+1,096
- CreatedAug 1, 2026
- First seen by usNov 7, 2026
- CheckedNov 11, 2026