colibri
What it does
An editorial selection.
Pure-C, zero-dependency engine that runs huge mixture-of-experts (MoE) models by keeping the active part in RAM and streaming experts from disk. No GPU needed.
Why it is listed
Run frontier-scale open models on an ordinary machine. 13 engine families so far.
GitHub describes it as: Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Counts were observed on 27/10/2026, 23:15:40 UTC. Observations older than 36 hours are excluded from current movement rankings.
Repository at a glance
- Stars
- 44,228
- Forks
- 5,035
- Open issues
- 74
- Merged PRs
- 1,487
- Commits, last 30 days
- 770
- Stars, 7 days
- unavailable
- Stars, 30 days
- unavailable
Counts observed on 27/10/2026, 23:15:40 UTC. Growth uses complete dated windows; see Methodology.
History
Project details
Explore and get started
Use the project's own documentation for supported platforms, dependencies and installation steps. The README and release notes are maintained by JustVugg.
- Read the README and setup instructionsFeatures, prerequisites, examples and documentation links.
- Browse releases and changelogsPublished versions and the changes made between releases.
- Check licence and usage termsApache-2.0 is the licence reported by GitHub; read the repository terms before use.
- Read pull requestsProposed changes and development discussions.
- Browse reported issuesKnown problems, feature requests and maintainer responses.
Development context
These are observations of work in the repository. They do not establish quality, security or support commitments.
- Total commits on default branch
- 3,738
- Open pull requests
- 73
- Closed issues, lifetime
- 520
- Median time to close an issue
- 2.3 days
- Median time to merge a pull request
- 0.8 days
Close and merge times use up to 20 most recently updated closed issues or merged pull requests. They omit unresolved work and are context, not a maintenance score. Sample limits.
Explore the same category
Other projects in Local AI Inference, ordered by shared topics and then name. These are discovery links, not equivalence claims.
- abhi245y/PS5LM-Plus
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
- AlexsJones/llmfit
TUI that inspects your CPU, RAM, GPU and VRAM and tells you which open models and quantizations will run well. It can also benchmark real tokens per second.
- antirez/ds4
"DwarfStar", a small native inference engine from Redis creator antirez for DeepSeek V4 Flash/PRO, GLM 5.x and Qwen3.8 on Metal, CUDA and ROCm.
- cobanov/PS5LM
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
Found an incorrect description or number? Send a correction with this page's address and a source.