What are the hardware requirements for Qwen1.5 MoE A2.7B?

Qwen1.5 MoE A2.7B requires approximately 28.7 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen1.5 MoE A2.7B and how large is it?

Qwen1.5 MoE A2.7B is developed by Qwen, a model with 14.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen1.5 MoE A2.7B perform on standard benchmarks?

Qwen1.5 MoE A2.7B has the following published scores: MMLU 62.54. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen1.5 MoE A2.7B by Qwen — VRAM 28.7GB, 8K context

Name: Qwen1.5 MoE A2.7B
Author: Qwen

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, HF Score: 56, LLM Explorer Score: 0.25, Arc: 54.9, HellaSwag: 79.4, MMLU: 62.5, TruthfulQA: 50.1, WinoGrande: 72.3, GSM8K: 17.

Autotrain compatible 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 Benchmarks

IFEval: 26.6 vs 88 (so35)^-69.8%

ARC: 54.86 vs 96.7 (so35)^-43.3%

HellaSwag: 79.39 vs 95.3 (gpt4)^-16.7%

MMLU: 62.54 vs 88.3 (so35)^-29.2%

TruthfulQA: 50.09 vs 59 (gpt4)^-15.1%

WinoGrande: 72.3 vs 87.5 (gpt4)^-17.4%

GSM8K: 16.98 vs 96.4 (so35)^-82.4%

MATH Lvl 5: 9.29

LLME Score: 0.25101

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Qwen1.5 MoE A2.7B (Qwen/Qwen1.5-MoE-A2.7B)

🌟 Advertise your project 🚀

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 Name	Qwen1.5 MoE A2.7B
Repository 🤗	https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B
Model Size	14.3b
Required VRAM	28.7 GB
Updated	2025-09-23
Maintainer	Qwen
Model Type	qwen2_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 Languages	en
Model Architecture	Qwen2MoeForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.39.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Best Alternatives to Qwen1.5 MoE A2.7B

Best Alternatives	Context / RAM	Downloads	Likes
...Aux Free Sft Math7k 1e 3 Gamma	8K / 28.7 GB	7	1
Qwen1.5 MoE Sft Math7k	8K / 57.3 GB	6	1
Qwen1.5 MoE A2.7B Wikihow	8K / 28.7 GB	19	4
...en1.5 MoE A2.7B Chat GPTQ Int4	32K / 8.4 GB	938	50

Rank the Qwen1.5 MoE A2.7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53254 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Qwen1.5 MoE A2.7B by Qwen

» All LLMs » Qwen » Qwen1.5 MoE A2.7B URL Share it on

Qwen1.5 MoE A2.7B Benchmarks

Qwen1.5 MoE A2.7B Parameters and Internals

Best Alternatives to Qwen1.5 MoE A2.7B

Rank the Qwen1.5 MoE A2.7B Capabilities

What open-source LLMs or SLMs are you in search of? 53254 in total.