What are the hardware requirements for Tiny Starcoder Py?

Tiny Starcoder Py requires approximately 0.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Tiny Starcoder Py and how large is it?

Tiny Starcoder Py is developed by bigcode, a model with 164.1m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Tiny Starcoder Py perform on standard benchmarks?

Tiny Starcoder Py has the following published scores: MMLU 26.79. Compare against reference models on this page or on the LLM Explorer leaderboards.

Tiny Starcoder Py by bigcode — VRAM 0.7GB

Name: Tiny Starcoder Py
Author: bigcode

Tiny Starcoder Py is an open-source language model by bigcode. Features: 164.1m LLM, VRAM: 0.7GB, License: bigcode-openrail-m, Code Generating, LLM Explorer Score: 0.2, Arc: 21, HellaSwag: 28.8, MMLU: 26.8, GSM8K: 1.

Code Codegen Dataset:bigcode/the-stack-dedu... Deploy:azure Endpoints compatible Gpt bigcode Model-index Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/bigcode/tiny_starcoder_py

Tiny Starcoder Py Benchmarks

ARC: 20.99 vs 96.7 (so35)^-78.3%

HellaSwag: 28.77 vs 95.3 (gpt4)^-69.8%

MMLU: 26.79 vs 88.3 (so35)^-69.7%

GSM8K: 0.99 vs 96.4 (so35)^-99%

LLME Score: 0.19745

^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)

Tiny Starcoder Py (bigcode/tiny_starcoder_py)

🌟 Advertise your project 🚀

Tiny Starcoder Py Parameters and Internals

Model Type

text generation

Use Cases

Primary Use Cases:

Assisted Generation

Training Details

Data Sources:

StarCoderData

Data Volume:

100 billion tokens

Context Length:

8000

Training Time:

18 hours

Hardware Used:

32 Tesla A100 GPUs

Model Architecture:

GPT-2 model with multi-query attention and Fill-in-the-Middle objective

Input Output

Input Format:

text (Python code)

Output Format:

generated code

LLM Name	Tiny Starcoder Py
Repository 🤗	https://huggingface.co/bigcode/tiny_starcoder_py
Model Size	164.1m
Required VRAM	0.7 GB
Updated	2026-05-21
Maintainer	bigcode
Model Type	gpt_bigcode
Model Files	0.7 GB 0.7 GB
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
License	bigcode-openrail-m
Transformers Version	4.28.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	float32
Activation Function	gelu_pytorch_tanh

Best Alternatives to Tiny Starcoder Py

Best Alternatives	Context / RAM	Downloads	Likes
Tiny Starplanner	0K / 0.7 GB	6	0
Rlhfmodel	0K / 0.7 GB	5	0
...4 Contract Summarization Step2	0K / 0.7 GB	8	0
...4 Contract Summarization Step1	0K / 0.7 GB	5	0
G24 BTECH PROJECT Step1	0K / 0.7 GB	6	0
G24 BTECH PROJECT Step2	0K / 0.7 GB	5	0
Tiny Starcoder Instruct	0K / 0.7 GB	40	1

Rank the Tiny Starcoder Py 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? 53999 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

Tiny Starcoder Py by bigcode

» All LLMs » bigcode » Tiny Starcoder Py URL Share it on

Tiny Starcoder Py Benchmarks

Tiny Starcoder Py Parameters and Internals

Best Alternatives to Tiny Starcoder Py

Rank the Tiny Starcoder Py Capabilities

What open-source LLMs or SLMs are you in search of? 53999 in total.