What are the hardware requirements for Starcoder2 3B AWQ?

Starcoder2 3B AWQ requires approximately 2.1 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Starcoder2 3B AWQ and how large is it?

Starcoder2 3B AWQ is developed by TechxGenus, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Starcoder2 3B AWQ perform on standard benchmarks?

Starcoder2 3B AWQ has the following published scores: MMLU 38.65, HumanEval (Python) 31.44. Compare against reference models on this page or on the LLM Explorer leaderboards.

Starcoder2 3B AWQ by TechxGenus — VRAM 2.1GB, 16K context

Name: Starcoder2 3B AWQ
Author: TechxGenus

Starcoder2 3B AWQ is an open-source language model by TechxGenus. Features: 3b LLM, VRAM: 2.1GB, Context: 16K, License: bigcode-openrail-m, Quantized, LLM Explorer Score: 0.16, Arc: 34.6, HellaSwag: 47.6, MMLU: 38.7, GSM8K: 19.6, HumanEval: 31.4.

Arxiv:2004.05150 Arxiv:2205.14135 Arxiv:2207.14255 Arxiv:2305.13245 4-bit Awq Code Dataset:bigcode/the-stack-v2-t... Endpoints compatible Model-index Quantized Region:us Safetensors Starcoder2

Model Card on HF 🤗: https://huggingface.co/TechxGenus/starcoder2-3b-AWQ

Starcoder2 3B AWQ Parameters and Internals

Model Type

text-generation

Use Cases

Primary Use Cases:

Generating code snippets

Limitations:

The generated code is not guaranteed to work as intended and can be inefficient, contain bugs, or exploits.

Supported Languages

main_language (English), other_languages_supported ()

Training Details

Data Sources:

bigcode/the-stack-v2-train

Data Volume:

3+ trillion tokens

Methodology:

Fill-in-the-Middle objective

Context Length:

16384

Hardware Used:

160 A100 GPUs

Model Architecture:

Transformer decoder with grouped-query and sliding window attention

Input Output

Accepted Modalities:

text

Output Format:

code snippets

LLM Name	Starcoder2 3B AWQ
Repository 🤗	https://huggingface.co/TechxGenus/starcoder2-3b-AWQ
Base Model(s)	Starcoder2 3B bigcode/starcoder2-3b
Model Size	3b
Required VRAM	2.1 GB
Updated	2026-08-02
Maintainer	TechxGenus
Model Type	starcoder2
Model Files	2.1 GB
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	Starcoder2ForCausalLM
License	bigcode-openrail-m
Context Length	16384
Model Max Length	16384
Transformers Version	4.39.3
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	float16

Rank the Starcoder2 3B AWQ 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

Best Alternatives to Starcoder2 3B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Starcoder2 3B 4bit	16K / 1.9 GB	88	1
Starcoder2 3B	16K / 12.1 GB	109597	220
Starcoder2 3b AutoRedteam	16K / 12.7 GB	5	0
Starcoder Proto Code	16K / 6.1 GB	7	0
Mojo Starcoder2	16K / 6.4 GB	11	0
StarCoder2 3B GGUF	16K / 1.1 GB	1964	20
NEARCoder 3B	16K / 6.1 GB	5	0
NEAR StructTunedStarcoder2	16K / 6.1 GB	7	0
NEAR PreTrainedStarCoder2	16K / 6.1 GB	5	0
Bigcode Starcoder2 3B 8bits	16K / 3.2 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/starcoder2-3b-AWQ.