What are the hardware requirements for Reyna Mini 1.8B V0.1?

Reyna Mini 1.8B V0.1 requires approximately 3.7 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 Reyna Mini 1.8B V0.1 and how large is it?

Reyna Mini 1.8B V0.1 is developed by aloobun, a model with 1.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Reyna Mini 1.8B V0.1 perform on standard benchmarks?

Reyna Mini 1.8B V0.1 has the following published scores: MMLU 45.37, LMSYS ELO 1259. Compare against reference models on this page or on the LLM Explorer leaderboards.

Reyna Mini 1.8B V0.1 by aloobun — VRAM 3.7GB, 32K context

Name: Reyna Mini 1.8B V0.1
Author: aloobun

Reyna Mini 1.8B V0.1 is an open-source language model by aloobun. Features: 1.8b LLM, VRAM: 3.7GB, Context: 32K, License: other, LLM Explorer Score: 0.27, ELO: 1259, Arc: 35.2, HellaSwag: 60.4, MMLU: 45.4, GSM8K: 5.5.

Chatml Conversational Custom code Dataset:teknium/openhermes-2.5 Endpoints compatible Finetuned Gpt4 Qwen2 Region:us Safetensors Sharded Synthetic data Tensorflow

Model Card on HF 🤗: https://huggingface.co/aloobun/Reyna-Mini-1.8B-v0.1

Reyna Mini 1.8B V0.1 Benchmarks

LMSys ELO 1259 vs 1272 (so35) -1%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Reyna Mini 1.8B V0.1 Parameters and Internals

Model Type

Finetuned, ChatML

Additional Notes

The inception of the Qwen1.5 LLM series, foundation model.

Training Details

Data Sources:

teknium/OpenHermes-2.5

Methodology:

Finetuning with SFT on teknium's OpenHermes-2.5 dataset.

Input Output

Input Format:

ChatML

Accepted Modalities:

text

Output Format:

Generated text completion

LLM Name	Reyna Mini 1.8B V0.1
Repository 🤗	https://huggingface.co/aloobun/Reyna-Mini-1.8B-v0.1
Model Size	1.8b
Required VRAM	3.7 GB
Updated	2026-07-23
Maintainer	aloobun
Model Type	qwen2
Model Files	3.0 GB: 1-of-2 0.7 GB: 2-of-2
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Reyna Mini 1.8B V0.1 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 Reyna Mini 1.8B V0.1

Best Alternatives	Context / RAM	Downloads	Likes
Palmyra Mini Thinking B	128K / 3.5 GB	35	27
Dhanishtha	128K / 3.5 GB	82	2
LaConfiance PRYMMAL ECE TW3	128K / 7.1 GB	6	0
Qwen1.5 1.8B Chat	32K / 3.7 GB	66688	75
Qwen1.5 1.8B	32K / 3.7 GB	67455	59
Qwen1.5 1.8B Chat Heretic	32K / 3.7 GB	8	0
Qwen1.5 1.8B Chat Heretic	32K / 3.7 GB	6	0
Colegium Ai 1.8B	32K / 3.7 GB	6	0
Qwen Fine Tuned V0	32K / 3.7 GB	6	0
Qwen1.5 1.8B Seed Sft	32K / 3.7 GB	12	0