What are the hardware requirements for Boris 250M?

Boris 250M requires approximately 1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Boris 250M and how large is it?

Boris 250M is developed by KSP-NMAI, a model with 250m 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 Boris 250M?

Boris 250M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Boris 250M by KSP-NMAI — VRAM 1GB

Name: Boris 250M
Author: KSP-NMAI

Boris 250M is an open-source language model by KSP-NMAI. Features: 250m LLM, VRAM: 1GB, License: apache-2.0, LLM Explorer Score: 0.27.

250m Boris Dataset:huggingfacefw/fineweb-... Dataset:mlfoundations/dclm-bas... En Endpoints compatible Gpt2 Nmai Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/KSP-NMAI/Boris-250M

Boris 250M Parameters and Internals

LLM Name	Boris 250M
Repository 🤗	https://huggingface.co/KSP-NMAI/Boris-250M
Model Size	250m
Required VRAM	1 GB
Updated	2026-07-30
Maintainer	KSP-NMAI
Model Type	gpt2
Model Files	1.0 GB
Supported Languages	en
Model Architecture	GPT2LMHeadModel
License	apache-2.0
Transformers Version	5.13.1
Tokenizer Class	GPTNeoXTokenizer
Padding Token	<\|padding\|>
Vocabulary Size	50304
Activation Function	gelu
Errors	replace

Rank the Boris 250M 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 Boris 250M

Best Alternatives	Context / RAM	Downloads	Likes
Boris 250M Instruct	0K / 1 GB	83	0
Boris 250M Instruct	0K / 1 GB	73	0

Note: green Score (e.g. "73.2") means that the model is better than KSP-NMAI/Boris-250M.