MG

GLM-5.2-colibri-int4-with-int8-mtp

Otherby Mateo Grguc·Model page

mateogrgic's INT4 quantization of GLM-5.2 optimized for CPU inference via expert streaming.

Share:

Base model

zai-org/GLM-5.2-FP8

Model Description

This is the *EXACT SAME THING* as https://huggingface.co/jlnsrk/GLM-5.2-colibri-int4, BUT with int8 MTP heads, which are needed for speculative decoding—and with that, an overall major inference speedboost. The original int4 MTP heads have low acceptance rate, and are essentially useless.

⚠️ This is NOT a GGUF / AWQ / GPTQ / MLX model. It only works with the colibrì engine.

Usage

# Get the engine
git clone https://github.com/JustVugg/colibri && cd colibri/c && ./setup.sh

# download this repo to a FAST local disk
hf download mateogrgic/GLM-5.2-colibri-int4-with-int8-mtp --local-dir /nvme/glm52

# run on CPU
COLI_MODEL=/nvme/glm52 ./coli chat

Requirements: Linux (or WSL2), gcc + OpenMP, AVX2, ≥16 GB RAM, ~400 GB free NVMe.

Provenance & license

Converted from zai-org/GLM-5.2-FP8 (MIT). This derivative is likewise MIT. Conversion performed with colibrì's official converter, unmodified. Cloned & modded from jlnsrk/GLM-5.2-colibri-int4

Author
MG
Mateo Grguc
User
mateogrgic
Details
Downloads6.8K
Likes76
AccessOpen Source
Trending61
Licensemit
CreatedJul 10, 2026
UpdatedJul 14, 2026
View on Hugging Face
Languages
enzh
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

GLM-5.2-colibri-int4-with-int8-mtp — AI Model Details | Applied