What are the hardware requirements for Qwen2.5 Coder 1.5B?

Qwen2.5 Coder 1.5B requires approximately 3.1 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen2.5 Coder 1.5B and how large is it?

Qwen2.5 Coder 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.

Where can I download or evaluate Qwen2.5 Coder 1.5B?

Qwen2.5 Coder 1.5B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen2.5 Coder 1.5B by Qwen — VRAM 3.1GB, 32K context

Name: Qwen2.5 Coder 1.5B
Author: Qwen

Qwen2.5 Coder 1.5B is an open-source language model by Qwen. Features: 1.5b LLM, VRAM: 3.1GB, Context: 32K, License: apache-2.0, Code Generating, LLM Explorer Score: 0.22.

Arxiv:2407.10671 Arxiv:2409.12186 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-1.5b Code Codegen Codeqwen Conversational Deploy:azure En Endpoints compatible Qwen Qwen-coder Qwen2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B

Qwen2.5 Coder 1.5B Parameters and Internals

Model Type

causal language model, code generation

Use Cases

Areas:

real-world applications, code agents

Applications:

code generation, code reasoning, code fixing

Limitations:

not recommended for conversation without post-training

Additional Notes

Model supports a long context up to 128k tokens using YaRN for length extrapolation.

Supported Languages

en (English)

Training Details

Data Sources:

source code, text-code grounding, synthetic data

Data Volume:

5.5 trillion tokens

Methodology:

Pretraining & Post-training

Context Length:

131072

Hardware Used:

transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings

Model Architecture:

transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings

Input Output

Accepted Modalities:

text

Performance Tips:

Recommend using vLLM for deployment with considerations for rope_scaling in long contexts.

LLM Name	Qwen2.5 Coder 1.5B
Repository 🤗	https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B
Base Model(s)	Qwen/Qwen2.5-1.5B Qwen/Qwen2.5-1.5B
Model Size	1.5b
Required VRAM	3.1 GB
Updated	2026-08-08
Maintainer	Qwen
Model Type	qwen2
Model Files	3.1 GB
Supported Languages	en
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.43.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen2.5 Coder 1.5B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Quantized Models of the Qwen2.5 Coder 1.5B

Model	Likes	Downloads	VRAM
Qwen2.5 Coder 1.5B Bnb 4bit	3	6123	1 GB
...en2.5 Coder 1.5B Instruct 4bit	2	2030	0 GB

Best Alternatives to Qwen2.5 Coder 1.5B

Best Alternatives	Context / RAM	Downloads	Likes
Pulsar Coder V1	128K / 3.1 GB	291	1
Merge Cord V1	128K / 3.1 GB	155	1
Replete Coder Qwen2 1.5B	128K / 3.1 GB	233	23
SlopCoder Mongo 1.5B Full	32K / 3.1 GB	64	0
Coder O1 Mini Reasoning	32K / 3.1 GB	644	0
Pulsar Coder 1.5B	32K / 3.1 GB	13	0
Qwen2.5 Coder 1.5B Instruct	32K / 3.1 GB	695585	134
Mythos Qwen 1.5B Final	32K / 3.1 GB	104	1
Microcoder 1.5B	32K / 3.1 GB	20	4
Qwen2.5 Coder 1.5B Instruct	32K / 3.1 GB	69796	6

Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-Coder-1.5B.