LLM EXPLORER 60,958 MODELS INDEXED

Smaug Mini by abacusai

By abacusai · 19 downloads
HF Repo ↗ Copy URL

Smaug Mini is an open-source language model by abacusai. Features: 27b LLM, VRAM: 55.6GB, License: apache-2.0, LLM Explorer Score: 0.27.

  Arxiv:2402.13228   Abacusai   Agentic Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.8-27b   Conversational   Endpoints compatible   Image-text-to-text   Qwen3 5   Region:us   Safetensors   Sharded   Smaug   Tensorflow
Model Card on HF 🤗: https://huggingface.co/abacusai/Smaug-Mini 

Smaug Mini Parameters and Internals

LLM NameSmaug Mini
Repository 🤗https://huggingface.co/abacusai/Smaug-Mini 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM55.6 GB
Updated2026-09-12
Maintainerabacusai
Model Typeqwen3_5
Model Files  4.0 GB: 1-of-18   3.0 GB: 2-of-18   2.5 GB: 3-of-18   4.0 GB: 4-of-18   2.1 GB: 5-of-18   4.0 GB: 6-of-18   2.1 GB: 7-of-18   4.0 GB: 8-of-18   2.1 GB: 9-of-18   4.0 GB: 10-of-18   2.1 GB: 11-of-18   4.0 GB: 12-of-18   2.1 GB: 13-of-18   4.0 GB: 14-of-18   2.1 GB: 15-of-18   4.0 GB: 16-of-18   2.1 GB: 17-of-18   3.4 GB: 18-of-18
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Smaug Mini

Best Alternatives
Context / RAM
Downloads
Likes
Agens Pilot1024K / 54.7 GB1271
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.8 27B NVFP40K / 22 GB1919574
Qwen3.6 27B FP80K / 0.4 GB7740472342
Cortex Mini 1 Preview0K / 55.6 GB1252
Note: green Score (e.g. "73.2") means that the model is better than abacusai/Smaug-Mini.