What are the hardware requirements for Control 8B V1.1?

Control 8B V1.1 requires approximately 16.1 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Control 8B V1.1 and how large is it?

Control 8B V1.1 is developed by Delta-Vector, a model with 8b 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 Control 8B V1.1?

Control 8B V1.1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Control 8B V1.1 by Delta-Vector — VRAM 16.1GB, 128K context

Name: Control 8B V1.1
Author: Delta-Vector

Control 8B V1.1 is an open-source language model by Delta-Vector. Features: 8b LLM, VRAM: 16.1GB, Context: 128K, License: agpl-3.0, Merged, LLM Explorer Score: 0.22.

Merged Model Chat Dataset:huggingfaceh4/ultrafee... Dataset:neweden/opencai-shareg... Dataset:neweden/roleplay-logs-... Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Delta-Vector/Control-8B-V1.1

Control 8B V1.1 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

chat, role-play

Applications:

text generation, AI assistant

Primary Use Cases:

character-based role-play

Limitations:

not suitable for NSFW content

Considerations:

Ensure contextual appropriateness for content.

Additional Notes

Designed to be 'Short and Sweet'.

Supported Languages

English (High)

Training Details

Data Sources:

NewEden/OpenCAI-ShareGPT, NewEden/Roleplay-Logs-Sharegpt-Ngram-cleaned, HuggingFaceH4/ultrafeedback_binarized

Methodology:

Finetuned for 2 epochs using DPO

Context Length:

1024

Hardware Used:

4 x RTX 3090 GPUs, 1 x Nvidia T4 GPU

Input Output

Input Format:

LLama-Instruct formatting

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use Euryale's or EVA system prompts for optimal performance.

LLM Name	Control 8B V1.1
Repository 🤗	https://huggingface.co/Delta-Vector/Control-8B-V1.1
Merged Model	Yes
Model Size	8b
Required VRAM	16.1 GB
Updated	2026-09-08
Maintainer	Delta-Vector
Model Type	llama
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4
Model Architecture	LlamaForCausalLM
License	agpl-3.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.45.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|finetune_right_pad_id\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Control 8B V1.1 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 Control 8B V1.1

Best Alternatives	Context / RAM	Downloads	Likes
...otron 8B UltraLong 4M Instruct	4192K / 32.1 GB	1135	125
UltraLong Thinking	4192K / 16.1 GB	2	3
...a 3.1 8B UltraLong 4M Instruct	4192K / 32.1 GB	176	24
...a 3.1 8B UltraLong 2M Instruct	2096K / 32.1 GB	875	9
...otron 8B UltraLong 2M Instruct	2096K / 32.1 GB	124	18
Cthulhu 8B V1.4	1048K / 16.1 GB	10	10
...raLong 1M Instruct Abliterated	1048K / 32.1 GB	4	9
...a 3.1 8B UltraLong 1M Instruct	1048K / 32.1 GB	1387	29
...otron 8B UltraLong 1M Instruct	1048K / 32.1 GB	702	59
...xis Bookwriter Llama3.1 8B Sft	1048K / 16.1 GB	25	4

Note: green Score (e.g. "73.2") means that the model is better than Delta-Vector/Control-8B-V1.1.