Colibrì Files

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine

This is an exact mirror of the Colibrì project, hosted at https://github.com/JustVugg/colibri. SourceForge is not affiliated with Colibrì.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	InfoDownloads / Week
v1.7.0	2026-08-20	1
v1.6.2	2026-08-14	0
v1.6.1	2026-08-13	0
v1.6.0	2026-08-12	0
v1.5.0	2026-08-05	4
Totals: 5 Items		5

Other Useful Business Software

$300 Free Credits to Build on Google Cloud

New customers can spin up VMs, build with AI, and query data at no cost.

Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.

Start Free

Custom VMs From 1 to 96 vCPUs With 99.95% Uptime

General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.

Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.

Try Free

$300 Free Credits to Build on Google Cloud

New customers can spin up VMs, build with AI, and query data at no cost.

Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.

Start Free

Recommended Projects

Kimi K3 in C
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU
WASTE
Run the full 2.78-trillion-parameter Kimi K3 model
GLM-4-Voice
GLM-4-Voice | End-to-End Chinese-English Conversational Model
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model
TurboFieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

Colibrì Files

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine

Get an email when there's a new version of Colibrì