LLM EXPLORER 60,587 MODELS INDEXED

Qwen1.5 1.8B Llamafy by raincandy-u

By raincandy-u · 7 downloads
HF Repo ↗ Copy URL

Qwen1.5 1.8B Llamafy is an open-source language model by raincandy-u. Features: 1.8b LLM, VRAM: 3.7GB, Context: 4K, License: other, LLM Explorer Score: 0.15, Arc: 37.5, HellaSwag: 61.4, MMLU: 46.8, GSM8K: 30.3.

  Chat   Conversational   En   Endpoints compatible   Llama   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/raincandy-u/Qwen1.5-1.8B_llamafy 

Qwen1.5 1.8B Llamafy Parameters and Internals

Model Type 
text-generation
Use Cases 
Applications:
academic research, computational linguistics
Limitations:
The converted model may generate more unpredictable responses compared to its original version.
Additional Notes 
This conversion of the Qwen model is intended for research and educational purposes only.
Supported Languages 
en (supported), zh (supported)
LLM NameQwen1.5 1.8B Llamafy
Repository 🤗https://huggingface.co/raincandy-u/Qwen1.5-1.8B_llamafy 
Model Size1.8b
Required VRAM3.7 GB
Updated2026-07-08
Maintainerraincandy-u
Model Typellama
Model Files  3.7 GB
Supported Languagesen zh
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 1.8B Llamafy

Best Alternatives
Context / RAM
Downloads
Likes
Ssh 1.8B8K / 3.7 GB870
EasyContext 256K Danube2 1.8B8K / 3.7 GB85
Llm Jp 3.1 1.8B Instruct44K / 3.7 GB360921
Llm Jp 3 1.8B4K / 3.7 GB896817
Llm Jp 3 1.8B Instruct4K / 3.7 GB576425
Llm Jp 3 1.8B Instruct34K / 3.7 GB6342
Llm Jp 3 1.8B Instruct4K / 3.7 GB70
Tinyllama 1.8B Trismegistus2K / 1.9 GB173
Llama1 S 1.8B Experimental2K / 7.3 GB34
TinyChat 1776K0.3K / 0 GB4512
Note: green Score (e.g. "73.2") means that the model is better than raincandy-u/Qwen1.5-1.8B_llamafy.