What are the hardware requirements for Qwen2 1.5B?

Qwen2 1.5B requires approximately 3.1 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen2 1.5B and how large is it?

Qwen2 1.5B is developed by Qwen, a model with 1.5b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen2 1.5B perform on standard benchmarks?

Qwen2 1.5B has the following published scores: MMLU 57.26. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen2 1.5B by Qwen — VRAM 3.1GB, 128K context

Name: Qwen2 1.5B
Author: Qwen

Qwen2 1.5B is an open-source language model by Qwen. Features: 1.5b LLM, VRAM: 3.1GB, Context: 128K, License: apache-2.0, HF Score: 55.8, LLM Explorer Score: 0.27, Arc: 44.3, HellaSwag: 66.7, MMLU: 57.3, TruthfulQA: 45.9, WinoGrande: 64.9, GSM8K: 55.8.

Conversational Deploy:azure En Endpoints compatible Pretrained Qwen2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2-1.5B

Qwen2 1.5B Benchmarks

IFEval: 21.13 vs 88 (so35)^-76%

ARC: 44.28 vs 96.7 (so35)^-54.2%

HellaSwag: 66.67 vs 95.3 (gpt4)^-30%

MMLU: 57.26 vs 88.3 (so35)^-35.2%

TruthfulQA: 45.92 vs 59 (gpt4)^-22.2%

WinoGrande: 64.88 vs 87.5 (gpt4)^-25.9%

GSM8K: 55.8 vs 96.4 (so35)^-42.1%

MATH Lvl 5: 7.02

LLME Score: 0.26753

^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)

🌟 Advertise your project 🚀

Qwen2 1.5B Parameters and Internals

Model Type

text generation

LLM Name	Qwen2 1.5B
Repository 🤗	https://huggingface.co/Qwen/Qwen2-1.5B
Model Size	1.5b
Required VRAM	3.1 GB
Updated	2026-05-07
Maintainer	Qwen
Model Type	qwen2
Model Files	3.1 GB
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.40.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Best Alternatives to Qwen2 1.5B

Best Alternatives	Context / RAM	Downloads	Likes
ReaderLM V2	500K / 3.1 GB	14849	779
Reader Lm 1.5B	250K / 3.1 GB	566	608
DeepSeek R1 Distill Qwen 1.5B	128K / 3.5 GB	830748	1465
VibeThinker 1.5B	128K / 3.5 GB	2025	520
Ko R1 1.5B Preview	128K / 7.1 GB	15	9
Qwen2.5 1.5B	128K / 3.1 GB	914961	176
AceInstruct 1.5B	128K / 3.5 GB	76880	20
1.5B Cold Start SFT	128K / 3.5 GB	4503	0
OpenReasoning Nemotron 1.5B	128K / 3.1 GB	7934	56
DeepScaleR 1.5B Preview	128K / 7.1 GB	7129	583

Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-1.5B.

Rank the Qwen2 1.5B 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? 53518 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

Qwen2 1.5B by Qwen

» All LLMs » Qwen » Qwen2 1.5B URL Share it on

Qwen2 1.5B Benchmarks

Qwen2 1.5B Parameters and Internals

Best Alternatives to Qwen2 1.5B

Rank the Qwen2 1.5B Capabilities

What open-source LLMs or SLMs are you in search of? 53518 in total.