LLM EXPLORER 60,828 MODELS INDEXED

Qwen1.5 MoE A2.7B by Qwen

By Qwen · 209172 downloads
HF Repo ↗ Copy URL

Qwen1.5 MoE A2.7B is an open-source language model by Qwen. Features: 14.3b LLM, VRAM: 28.7GB, Context: 8K, License: other, MoE, LLM Explorer Score: 0.26, Arc: 54.9, HellaSwag: 79.4, MMLU: 62.5, GSM8K: 17.

  Conversational   En   Endpoints compatible   Moe   Pretrained   Qwen2 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B 

Qwen1.5 MoE A2.7B Parameters and Internals

Model Type 
text-generation
Additional Notes 
Qwen1.5-MoE employs a Mixture of Experts (MoE) architecture, with 14.3B parameters total and 2.7B activated during runtime. It's optimized for performance and efficiency, with only 25% of the training resources compared to similar models. The model is available on Hugging Face and requires the latest transformers library for implementation.
Supported Languages 
en (native)
LLM NameQwen1.5 MoE A2.7B
Repository 🤗https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B 
Model Size14.3b
Required VRAM28.7 GB
Updated2026-07-03
MaintainerQwen
Model Typeqwen2_moe
Model Files  4.0 GB: 1-of-8   4.0 GB: 2-of-8   4.0 GB: 3-of-8   4.0 GB: 4-of-8   4.0 GB: 5-of-8   4.0 GB: 6-of-8   4.0 GB: 7-of-8   0.7 GB: 8-of-8
Supported Languagesen
Model ArchitectureQwen2MoeForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.39.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 MoE A2.7B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen1.5 MoE A2.7B Chat32K / 28.7 GB40226133
Qwen1.5 MoE A2.7B8K / 28.7 GB2230
...Aux Free Sft Math7k 1e 3 Gamma8K / 28.7 GB61
Qwen1.5 MoE Sft Math7k8K / 57.3 GB51
Qwen1.5 MoE A2.7B Wikihow8K / 28.7 GB114
...en1.5 MoE A2.7B Chat GPTQ Int432K / 8.4 GB215550
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-MoE-A2.7B.