What are the hardware requirements for Dromedary 65B Lora GPTQ?

Dromedary 65B Lora GPTQ requires approximately 33.5 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dromedary 65B Lora GPTQ and how large is it?

Dromedary 65B Lora GPTQ is developed by TheBloke, a model with 65b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Dromedary 65B Lora GPTQ perform on standard benchmarks?

Dromedary 65B Lora GPTQ has the following published scores: MMLU 63.08. Compare against reference models on this page or on the LLM Explorer leaderboards.

Dromedary 65B Lora GPTQ by TheBloke — VRAM 33.5GB, 2K context

Name: Dromedary 65B Lora GPTQ
Author: TheBloke

Dromedary 65B Lora GPTQ is an open-source language model by TheBloke. Features: 65b LLM, VRAM: 33.5GB, Context: 2K, License: other, Quantized, LLM Explorer Score: 0.09, Arc: 61.6, HellaSwag: 82.5, MMLU: 63.1, GSM8K: 27.5.

4-bit Gptq Llama Lora Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/dromedary-65B-lora-GPTQ

Dromedary 65B Lora GPTQ Parameters and Internals

Model Type

Language Model, Transformer

Use Cases

Areas:

Research

Applications:

Model alignment studies

Primary Use Cases:

Research in AI alignment

Additional Notes

Model is configured for use with text-generation-webui.

Supported Languages

English (Proficient)

Training Details

Data Sources:

Human annotations and seed prompts

Data Volume:

<300 lines of human annotations

Methodology:

LoRA with GPTQ quantisation

Training Time:

April 2023 to May 2023

Model Architecture:

Transformer

Input Output

Input Format:

Text prompt

Accepted Modalities:

Text

Output Format:

Text

Performance Tips:

Limit responses to <1500 tokens for systems with 48GB VRAM.

LLM Name	Dromedary 65B Lora GPTQ
Repository 🤗	https://huggingface.co/TheBloke/dromedary-65B-lora-GPTQ
Base Model(s)	Dromedary 65B Lora HF TheBloke/dromedary-65b-lora-HF
Model Size	65b
Required VRAM	33.5 GB
Updated	2026-07-17
Maintainer	TheBloke
Model Type	llama
Model Files	33.5 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
LoRA Model	Yes
Torch Data Type	float16

Rank the Dromedary 65B Lora GPTQ 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 Dromedary 65B Lora GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...en Instruct Human Mix 65B GPTQ	2K / 33.5 GB	11	0
Airoboros 65B Gpt4 1.4 GPTQ	2K / 33.5 GB	12	13
Airoboros 65B Gpt4 1.3 GPTQ	2K / 33.5 GB	5	3
Airoboros 65B Gpt4 1.2 GPTQ	2K / 33.5 GB	41	11
Gpt4 Alpaca Lora Mlp 65B GPTQ	2K / 33.5 GB	49	14
Guanaco 65B GPTQ	2K / 33.5 GB	481	262
Airoboros 65B GPT4 2.0 GPTQ	2K / 33.5 GB	8	3
Airoboros 65B GPT4 M2.0 GPTQ	2K / 33.5 GB	3	2
...stage Llama1 65B Instruct GPTQ	2K / 34.7 GB	9	3
...Research Oasst1 Llama 65B GPTQ	2K / 33.5 GB	11	5

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/dromedary-65B-lora-GPTQ.