What are the hardware requirements for TinyBalls 110M V1?

TinyBalls 110M V1 requires approximately 0.5 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TinyBalls 110M V1 and how large is it?

TinyBalls 110M V1 is developed by igidn, a model with 110m 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 TinyBalls 110M V1?

TinyBalls 110M V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TinyBalls 110M V1 by igidn — VRAM 0.5GB, 32K context

Name: TinyBalls 110M V1
Author: igidn

TinyBalls 110M V1 is an open-source language model by igidn. Features: 110m LLM, VRAM: 0.5GB, Context: 32K, License: mit, LLM Explorer Score: 0.31.

Base model:finetune:igidn/tiny... Base model:igidn/tinyballs-v1-... Conversational Dataset:igidn/tool-failure-rec... Dataset:interstellarninja/herm... Dataset:nousresearch/hermes-fu... Dataset:nvidia/nemotron-sft-ag... Dataset:nvidia/nemotron-sft-ar... Dataset:nvidia/nemotron-sft-sc... Dataset:nvidia/when2call Dataset:product-science/xlam-f... Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/igidn/TinyBalls-110M-V1

TinyBalls 110M V1 Parameters and Internals

LLM Name	TinyBalls 110M V1
Repository 🤗	https://huggingface.co/igidn/TinyBalls-110M-V1
Base Model(s)	TinyBalls V1 Base igidn/TinyBalls-v1-Base
Model Size	110m
Required VRAM	0.5 GB
Updated	2026-10-08
Maintainer	igidn
Model Type	llama
Model Files	0.5 GB
Model Architecture	LlamaForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	49154
Torch Data Type	float32

Rank the TinyBalls 110M V1 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 TinyBalls 110M V1

Best Alternatives	Context / RAM	Downloads	Likes
BigWeave V20 110B	4K / 220 GB	51	0
...10M Experimental V0.1 Instruct	1K / 0.2 GB	36	1
HelpingAI 110M	1K / 0.2 GB	508	2
Tinybooks 110M Idiot Iter1000	1K / 0.4 GB	6	0
TinyStoriesChinese 110M	1K / 0.4 GB	5	1
Tinyllama 110M Fp32	1K / 0.4 GB	1480	0
Llama 110M	1K / 0.2 GB	11	0
Tinyllama 110M	1K / 0.2 GB	866	6