LLM EXPLORER 55,709 MODELS INDEXED

GLM 4.5 GPTQ Int4 Int8Mix by QuantTrio

By QuantTrio · 6 downloads
HF Repo ↗ Copy URL

GLM 4.5 GPTQ Int4 Int8Mix is an open-source language model by QuantTrio. Features: 55.3b LLM, VRAM: 205.2GB, Context: 128K, Quantized, LLM Explorer Score: 0.19.

  4-bit Base model:quantized:zai-org/g...   Base model:zai-org/glm-4.5   Conversational   Endpoints compatible   Glm4 moe   Gptq   Gptq marlin   Int4-int8mix   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm   量化修复
Model Card on HF 🤗: https://huggingface.co/QuantTrio/GLM-4.5-GPTQ-Int4-Int8Mix 

GLM 4.5 GPTQ Int4 Int8Mix Parameters and Internals

LLM NameGLM 4.5 GPTQ Int4 Int8Mix
Repository 🤗https://huggingface.co/QuantTrio/GLM-4.5-GPTQ-Int4-Int8Mix 
Base Model(s)  zai-org/GLM-4.5   zai-org/GLM-4.5
Model Size55.3b
Required VRAM205.2 GB
Updated2026-07-18
MaintainerQuantTrio
Model Typeglm4_moe
Model Files  5.0 GB: 1-of-42   5.0 GB: 2-of-42   5.0 GB: 3-of-42   5.0 GB: 4-of-42   5.0 GB: 5-of-42   5.0 GB: 6-of-42   5.0 GB: 7-of-42   5.0 GB: 8-of-42   5.0 GB: 9-of-42   5.0 GB: 10-of-42   5.0 GB: 11-of-42   5.0 GB: 12-of-42   5.0 GB: 13-of-42   5.0 GB: 14-of-42   5.0 GB: 15-of-42   5.0 GB: 16-of-42   5.0 GB: 17-of-42   5.0 GB: 18-of-42   5.0 GB: 19-of-42   5.0 GB: 20-of-42   5.0 GB: 21-of-42   5.0 GB: 22-of-42   5.0 GB: 23-of-42   5.0 GB: 24-of-42   5.0 GB: 25-of-42   5.0 GB: 26-of-42   5.0 GB: 27-of-42   5.0 GB: 28-of-42   5.0 GB: 29-of-42   5.0 GB: 30-of-42   5.0 GB: 31-of-42   5.0 GB: 32-of-42   5.0 GB: 33-of-42   5.0 GB: 34-of-42   5.0 GB: 35-of-42   5.0 GB: 36-of-42   5.0 GB: 37-of-42   5.0 GB: 38-of-42   3.9 GB: 39-of-42   5.0 GB: 40-of-42   5.0 GB: 41-of-42   1.3 GB: 42-of-42
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureGlm4MoeForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.54.0
Vocabulary Size151552
Torch Data Typefloat16