What are the hardware requirements for Theory Of Mind 128 StableLM?

Theory Of Mind 128 StableLM requires approximately 0.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Theory Of Mind 128 StableLM and how large is it?

Theory Of Mind 128 StableLM is developed by jeiku, a model with 3b 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 Theory Of Mind 128 StableLM?

Theory Of Mind 128 StableLM is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Theory Of Mind 128 StableLM by jeiku — VRAM 0.7GB

Name: Theory Of Mind 128 StableLM
Author: jeiku

Theory Of Mind 128 StableLM is an open-source language model by jeiku. Features: 3b LLM, VRAM: 0.7GB, License: cc-by-sa-4.0, LLM Explorer Score: 0.1.

4-bit Adapter Base model:adapter:stabilityai... Base model:stabilityai/stablel... Bitsandbytes Custom code Finetuned Generated from trainer Lora Peft Region:us Stablelm epoch

Model Card on HF 🤗: https://huggingface.co/jeiku/Theory_of_Mind_128_StableLM

Theory Of Mind 128 StableLM Parameters and Internals

Model Type

AutoModelForCausalLM

Training Details

Data Sources:

theory_of_mind_airoboros_fixed.json

Context Length:

1024

LLM Name	Theory Of Mind 128 StableLM
Repository 🤗	https://huggingface.co/jeiku/Theory_of_Mind_128_StableLM
Base Model(s)	Stablelm 3B 4e1t stabilityai/stablelm-3b-4e1t
Model Size	3b
Required VRAM	0.7 GB
Updated	2026-04-06
Maintainer	jeiku
Model Files	0.7 GB
Model Architecture	Adapter
License	cc-by-sa-4.0
Is Biased	none
Tokenizer Class	GPTNeoXTokenizer
Padding Token	[PAD]
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	v_proj\|q_proj
LoRA Alpha	256
LoRA Dropout	0.05
R Param	128

Rank the Theory Of Mind 128 StableLM 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 Theory Of Mind 128 StableLM

Best Alternatives	Context / RAM	Downloads	Likes
AIBio LoRA	0K / 0.1 GB	28	1
... 3B Oracle Nl2sql Lora Adapter	0K / 0 GB	28	1
StandardOne 3B LoRA	0K / 0.1 GB	42	1
...racle Text To Sql Lora Adapter	0K / 0 GB	22	1
Qwen2.5 VL 3B FakeBench LoRA	0K / 0.1 GB	19	1
Talvion Support Sft Kb V2 Lora	0K / 0.1 GB	10	0
...2.5 3B Instruct Sheldon SFT V2	0K / 0.2 GB	9	1
Running Coach Qwen3b Lora	0K / 0.1 GB	27	1
...wen2.5 Vl 3B Food Extract Lora	0K / 0.1 GB	15	1
Qwen Darija Domain Adapted	0K / 0.1 GB	14	1

Note: green Score (e.g. "73.2") means that the model is better than jeiku/Theory_of_Mind_128_StableLM.