What are the hardware requirements for Coven Tiny 1.1B 32K Orpo Alpha?

Coven Tiny 1.1B 32K Orpo Alpha requires approximately 2.2 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 Coven Tiny 1.1B 32K Orpo Alpha and how large is it?

Coven Tiny 1.1B 32K Orpo Alpha is developed by raidhon, a model with 1.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Coven Tiny 1.1B 32K Orpo Alpha perform on standard benchmarks?

Coven Tiny 1.1B 32K Orpo Alpha has the following published scores: MMLU 38.53. Compare against reference models on this page or on the LLM Explorer leaderboards.

Coven Tiny 1.1B 32K Orpo Alpha by raidhon — VRAM 2.2GB, 32K context

Name: Coven Tiny 1.1B 32K Orpo Alpha
Author: raidhon

Coven Tiny 1.1B 32K Orpo Alpha is an open-source language model by raidhon. Features: 1.1b LLM, VRAM: 2.2GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.16, Arc: 37.2, HellaSwag: 53.7, MMLU: 38.5, GSM8K: 14.

Base model:finetune:tinyllama/... Base model:tinyllama/tinyllama... Conversational En Endpoints compatible Llama Model-index Orpo Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/raidhon/coven_tiny_1.1b_32k_orpo_alpha

Coven Tiny 1.1B 32K Orpo Alpha Parameters and Internals

Model Type

text-generation, large-language-model

Additional Notes

Coven Tiny 1.1B 32K uses the innovative ORPO (Monolithic Preference Optimization without Reference Model) technique, which simplifies the fine-tuning process by directly optimizing the odds ratio.

Supported Languages

multilingual (unknown)

LLM Name	Coven Tiny 1.1b 32k Orpo Alpha
Repository 🤗	https://huggingface.co/raidhon/coven_tiny_1.1b_32k_orpo_alpha
Base Model(s)	TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama/TinyLlama-1.1B-Chat-v1.0
Model Size	1.1b
Required VRAM	2.2 GB
Updated	2026-07-23
Maintainer	raidhon
Model Type	llama
Model Files	2.2 GB
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Coven Tiny 1.1B 32K Orpo Alpha 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 Coven Tiny 1.1B 32K Orpo Alpha

Best Alternatives	Context / RAM	Downloads	Likes
TinyKiller NSFW DPO 1.1B	32K / 2.2 GB	12	0
Test Mix 01	32K / 2.2 GB	5	0
Palmer Merge Test 5	32K / 2.2 GB	5	0
TinyLlama 1.1B 32K Instruct	32K / 2.2 GB	3123	13
...llama 1.1B 16K Instructions V4	32K / 2.2 GB	8	0
TinyJ.O.S.I.E. 1.1B 32K Base	32K / 2.2 GB	30	1
Palmer 002 32K	32K / 2.2 GB	9	0
TinyJ.O.S.I.E. 1.1B 32K Base	32K / 2.2 GB	5	1
...lama 1.1B 16K Instructions Rag	32K / 2.2 GB	25	0
TinyLlama 1.1B 32K	32K / 2.2 GB	76	30

Note: green Score (e.g. "73.2") means that the model is better than raidhon/coven_tiny_1.1b_32k_orpo_alpha.