---
license: mit
base_model: jlnsrk/GLM-5.2-colibri-int4
library_name: colibri
pipeline_tag: text-generation
tags:
  - glm_moe_dsa
  - glm-5.2
  - colibri
  - int4
  - moe
  - custom-format
---

# GLM-5.2 FP8 Uncensored — Colibri int4

This is a **Colibri-compatible int4 conversion** of [zandenAI/GLM-5.2-FP8-Uncensored](https://huggingface.co/zandenAI/GLM-5.2-FP8-Uncensored).

It was created for [JustVugg/colibri](https://github.com/JustVugg/colibri): a C inference engine that keeps the dense part in RAM and streams routed MoE experts from local storage.

> This is an independent conversion, not an official Z.ai, NVIDIA, or Hugging Face release.

## Important compatibility note

This repository is **not** a standard Transformers, vLLM, SGLang, AWQ, or GGUF checkpoint. The tensors use Colibri's custom safetensors container and quantization layout. Use it with Colibri; do not expect `AutoModelForCausalLM.from_pretrained()` to load it.

## Quantization layout

- Routed expert and ordinary linear weights: Colibri row-wise **int4**.
- Token embedding and LM head: **int8**.
- Norms and routing weights: **FP32**.
- DSA indexer and MTP head: **int8**.

The source FP8 tensors are dequantized, then requantized into Colibri's format. The original FP8 checkpoint is not included here.

## Files

- `out-*.safetensors` — main model shards.
- `out-idx-*.safetensors` — DSA / IndexShare indexer weights.
- `out-mtp-*.safetensors` — MTP head for speculative decoding.
- `config.json`, tokenizer files, and generation config — model metadata.

All three groups are required for the complete conversion.

## Usage

Follow the build and runtime instructions in the [Colibri README](https://github.com/JustVugg/colibri#readme). Download the complete repository to fast local storage; Colibri streams expert shards from disk during inference.

## License

The source model repository declares the [MIT License](https://huggingface.co/zandenAI/GLM-5.2-FP8-Uncensored). This conversion is released under MIT on the same basis; please also review and comply with the upstream model terms.

## Credits

- Source model: [zandenAI/GLM-5.2-FP8-Uncensored](https://huggingface.co/zandenAI/GLM-5.2-FP8-Uncensored)
- Runtime and original conversion approach: [JustVugg/colibri](https://github.com/JustVugg/colibri)