LLM EXPLORER 59,598 MODELS INDEXED

Apodex 1.1 Mini GPTQ Int4 by apodex

By apodex · 177 downloads
HF Repo ↗ Copy URL

Apodex 1.1 Mini GPTQ Int4 is an open-source language model by apodex. Features: 36b LLM, VRAM: 22.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.37.

  Arxiv:2608.23283   4-bit   Agent   Apodex Base model:apodex/apodex-1.1-m... Base model:quantized:apodex/ap...   Conversational   En   Endpoints compatible   Gptq   Image-text-to-text   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/apodex/Apodex-1.1-mini-GPTQ-Int4 

Apodex 1.1 Mini GPTQ Int4 Parameters and Internals

LLM NameApodex 1.1 Mini GPTQ Int4
Repository 🤗https://huggingface.co/apodex/Apodex-1.1-mini-GPTQ-Int4 
Base Model(s)  apodex/Apodex-1.1-mini   apodex/Apodex-1.1-mini
Model Size36b
Required VRAM22.9 GB
Updated2026-08-26
Maintainerapodex
Model Typeqwen3_5_moe
Model Files  4.3 GB: 1-of-6   4.3 GB: 2-of-6   4.3 GB: 3-of-6   4.3 GB: 4-of-6   3.7 GB: 5-of-6   2.0 GB: 6-of-6   1.7 GB
Supported Languagesen zh
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Apodex 1.1 Mini GPTQ Int4

Best Alternatives
Context / RAM
Downloads
Likes
Apodex 1.1 Mini FP80K / 37.6 GB23514
Affine 5eqdtdzqle Ckpt300 M40K / 142.6 GB5480
Darwin 35B A3B Opus0K / 72.3 GB19497
Yaya 3.60K / 72.2 GB380
Carnice Qwen3.6 MoE 35B A3B0K / 72.2 GB023
Qwopus MoE 35B A3B0K / 72.3 GB311