What are the hardware requirements for Pythia 31M KI V1 2048 Scratch?

Pythia 31M KI V1 2048 Scratch requires approximately 0.1 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Pythia 31M KI V1 2048 Scratch and how large is it?

Pythia 31M KI V1 2048 Scratch is developed by pszemraj, a model with 31m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Pythia 31M KI V1 2048 Scratch perform on standard benchmarks?

Pythia 31M KI V1 2048 Scratch has the following published scores: MMLU 23.12. Compare against reference models on this page or on the LLM Explorer leaderboards.

Pythia 31M KI V1 2048 Scratch by pszemraj — VRAM 0.1GB, 2K context

Name: Pythia 31M KI V1 2048 Scratch
Author: pszemraj

Pythia 31M KI V1 2048 Scratch is an open-source language model by pszemraj. Features: 31m LLM, VRAM: 0.1GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.14, Arc: 23.1, HellaSwag: 25.2, MMLU: 23.1.

En Endpoints compatible Generated from trainer Gpt neox Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/pszemraj/pythia-31m-KI_v1-2048-scratch

Pythia 31M KI V1 2048 Scratch Parameters and Internals

Model Type

text-generation

Additional Notes

Model initialized from random weights based on the configuration of EleutherAI/pythia-31m.

Supported Languages

en (English)

Training Details

Context Length:

2048

Release Notes

Version:

base

Version:

1.0.0

Notes:

Initial release with random weights.

LLM Name	Pythia 31M KI V1 2048 Scratch
Repository 🤗	https://huggingface.co/pszemraj/pythia-31m-KI_v1-2048-scratch
Model Size	31m
Required VRAM	0.1 GB
Updated	2026-08-06
Maintainer	pszemraj
Model Type	gpt_neox
Model Files	0.1 GB 0.0 GB
Supported Languages	en
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.33.1
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50304
Torch Data Type	float32

Rank the Pythia 31M KI V1 2048 Scratch 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 Pythia 31M KI V1 2048 Scratch

Best Alternatives	Context / RAM	Downloads	Likes
Pythia 31M	2K / 0.1 GB	20717	1
Pythia 31M Chat V1	2K / 0.1 GB	181	8
...implepile Lite 2048 Scratch 2e	2K / 0.1 GB	75	0
...ia 31M Simplewiki Scratch Bf16	2K / 0.1 GB	53	0
... Goodwiki Deduped 2048 Scratch	2K / 0.1 GB	77	1
Pythia 31M Simplewiki 2048	2K / 0.1 GB	51	1
Pythia 31M	2K / 0.1 GB	11	0
...31M SimpleRW Lite 2048 Scratch	2K / 0.1 GB	5	1

Note: green Score (e.g. "73.2") means that the model is better than pszemraj/pythia-31m-KI_v1-2048-scratch.