What are the hardware requirements for Starcoder2 15B AWQ?

Starcoder2 15B AWQ requires approximately 9.2 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 15B AWQ and how large is it?

Starcoder2 15B AWQ is developed by TechxGenus, a model with 15b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Starcoder2 15B AWQ perform on standard benchmarks?

Starcoder2 15B AWQ has the following published scores: MMLU 51.35, HumanEval (Python) 44.15. Compare against reference models on this page or on the LLM Explorer leaderboards.

Starcoder2 15B AWQ by TechxGenus — VRAM 9.2GB, 16K context

Name: Starcoder2 15B AWQ
Author: TechxGenus

Starcoder2 15B AWQ is an open-source language model by TechxGenus. Features: 15b LLM, VRAM: 9.2GB, Context: 16K, License: bigcode-openrail-m, Quantized, LLM Explorer Score: 0.14, Arc: 47.4, HellaSwag: 64.1, MMLU: 51.4, GSM8K: 52.2, HumanEval: 44.2.

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 Sharded Starcoder2 Tensorflow

Model Card on HF 🤗: https://huggingface.co/TechxGenus/starcoder2-15b-AWQ

Starcoder2 15B AWQ Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

text generation from code

Limitations:

Generated code may be inefficient, contain bugs or exploits.

Training Details

Data Sources:

The Stack v2, GitHub, Arxiv, Wikipedia

Data Volume:

4+ trillion tokens

Methodology:

Grouped Query Attention, sliding window attention, Fill-in-the-Middle objective

Context Length:

16384

Hardware Used:

NVIDIA Eos Supercomputer, NVIDIA DGX H100

Model Architecture:

Transformer decoder

Input Output

Input Format:

Python script or function snippets

Accepted Modalities:

text

Output Format:

Generated text or code snippets

LLM Name	Starcoder2 15B AWQ
Repository 🤗	https://huggingface.co/TechxGenus/starcoder2-15b-AWQ
Base Model(s)	Starcoder2 15B bigcode/starcoder2-15b
Model Size	15b
Required VRAM	9.2 GB
Updated	2026-07-11
Maintainer	TechxGenus
Model Type	starcoder2
Model Files	5.0 GB: 1-of-2 4.2 GB: 2-of-2
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 15B 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 15B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Starchat2 15B V0.1 AWQ	16K / 9.2 GB	5	0
Speechless Starcoder2 15B	16K / 31.9 GB	9	3
Starcoder2 15B	16K / 63.8 GB	8388	674
Starcoder2 15B Instruct V0.1	16K / 31.9 GB	597	105
...rCoder2 15B Instruct V0.1 GGUF	16K / 6.2 GB	412	0
StarCoder2 15B GGUF	16K / 6.2 GB	1731	31
...rCoder2 15B Instruct V0.1 GGUF	16K / 6.2 GB	261	0
Starcoder2 15B Finetuned Drake	16K / 63.8 GB	7	0
CodeFuse StarCoder2 15B	16K / 31.9 GB	18	1
Starchat2 15B V0.1	16K / 31.9 GB	352	112

Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/starcoder2-15b-AWQ.