LLM EXPLORER 64,924 MODELS INDEXED

Qwen3.8 23B Mini Me Bf16 by StargazerLabs

By StargazerLabs · 103 downloads
HF Repo ↗ Copy URL

Qwen3.8 23B Mini Me Bf16 is an open-source language model by StargazerLabs. Features: 27b LLM, VRAM: 45.7GB, License: apache-2.0, LLM Explorer Score: 0.26.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.8-27b   Conversational   Image-text-to-text   Layer-pruning   Mlx   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/StargazerLabs/Qwen3.8-23B-Mini-Me-bf16 

Qwen3.8 23B Mini Me Bf16 Parameters and Internals

LLM NameQwen3.8 23B Mini Me Bf16
Repository 🤗https://huggingface.co/StargazerLabs/Qwen3.8-23B-Mini-Me-bf16 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM45.7 GB
Updated2026-08-21
MaintainerStargazerLabs
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-11   4.7 GB: 2-of-11   4.7 GB: 3-of-11   4.8 GB: 4-of-11   4.7 GB: 5-of-11   4.8 GB: 6-of-11   4.8 GB: 7-of-11   4.8 GB: 8-of-11   4.8 GB: 9-of-11   4.8 GB: 10-of-11   0.3 GB: 11-of-11
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Quantized Models of the Qwen3.8 23B Mini Me Bf16

Model
Likes
Downloads
VRAM
Qwen3.8 23B Mini Me 4bit423213 GB
Qwen3.8 23B Mini Me 8bit19424 GB

Best Alternatives to Qwen3.8 23B Mini Me Bf16

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB933
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB210942217
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.6 27B NVFP40K / 22 GB1887525419
Note: green Score (e.g. "73.2") means that the model is better than StargazerLabs/Qwen3.8-23B-Mini-Me-bf16.