LLM EXPLORER 59,182 MODELS INDEXED

Qwen3.8 23B Mini Me 4bit by StargazerLabs

By StargazerLabs · 232 downloads
HF Repo ↗ Copy URL

Qwen3.8 23B Mini Me 4bit is an open-source language model by StargazerLabs. Features: 23b LLM, VRAM: 13.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.33.

  4-bit   4bit Base model:quantized:stargazer... Base model:stargazerlabs/qwen3...   Conversational   Image-text-to-text   Layer-pruning   Mlx   Quantized   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/StargazerLabs/Qwen3.8-23B-Mini-Me-4bit 

Qwen3.8 23B Mini Me 4bit Parameters and Internals

LLM NameQwen3.8 23B Mini Me 4bit
Repository 🤗https://huggingface.co/StargazerLabs/Qwen3.8-23B-Mini-Me-4bit 
Base Model(s)  StargazerLabs/Qwen3.8-23B-Mini-Me-bf16   StargazerLabs/Qwen3.8-23B-Mini-Me-bf16
Model Size23b
Required VRAM13.4 GB
Updated2026-08-21
MaintainerStargazerLabs
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   2.8 GB: 3-of-3
Quantization Type4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 23B Mini Me 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 23B Mini Me 8bit0K / 24.5 GB941