What are the hardware requirements for QCammel 70 X AWQ?

QCammel 70 X AWQ requires approximately 36.6 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed QCammel 70 X AWQ and how large is it?

QCammel 70 X AWQ is developed by TheBloke, a model with 69b 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 QCammel 70 X AWQ?

QCammel 70 X AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

QCammel 70 X AWQ by TheBloke — VRAM 36.6GB, 4K context

Name: QCammel 70 X AWQ
Author: TheBloke

QCammel 70 X AWQ is an open-source language model by TheBloke. Features: 69b LLM, VRAM: 36.6GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.09.

Arxiv:2302.70971 Arxiv:2305.12031 Arxiv:2305.14314 4-bit Awq Base model:augtoma/qcammel-70-... Base model:quantized:augtoma/q... En Llama Llama2 Pytorch Qcammel-70 Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheBloke/qCammel-70-x-AWQ

QCammel 70 X AWQ Parameters and Internals

Model Type

llama, text generation

Use Cases

Areas:

academic medical knowledge, instruction-following

Additional Notes

qCammel-70 is a fine-tuned version optimized for academic medical knowledge and instruction-following using QLoRA.

Training Details

Data Sources:

Distilled dataset of 15,000 instructions

Methodology:

QLoRA

Context Length:

4096

Model Architecture:

Llama 2 architecture, an auto-regressive language model that uses a decoder only transformer architecture.

Input Output

Input Format:

Text input

Accepted Modalities:

Text

Output Format:

Text output

LLM Name	QCammel 70 X AWQ
Repository 🤗	https://huggingface.co/TheBloke/qCammel-70-x-AWQ
Model Name	qCammel 70
Model Creator	augtoma
Base Model(s)	QCammel 70 X augtoma/qCammel-70-x
Model Size	69b
Required VRAM	36.6 GB
Updated	2026-07-31
Maintainer	TheBloke
Model Type	llama
Model Files	9.9 GB: 1-of-4 9.9 GB: 2-of-4 9.9 GB: 3-of-4 6.9 GB: 4-of-4
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.32.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the QCammel 70 X AWQ 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 QCammel 70 X AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...ine Tu Ophtho 3 1e 05 Stanford	4K / 138.7 GB	5	0
StableBeluga2	4K / 1.7 GB	15937	20
V Alpha Tross	4K / 138.7 GB	74	20
Uni TianYan V1	4K / 138 GB	66	0
SaiLy Experiment V1	4K / 276 GB	15	2
Airoboros L2 C70b 3.1.2	4K / 138 GB	79	0
Model 007 Preview	4K / 138 GB	29	1
QCammel 70 X GPTQ	4K / 35.3 GB	10	2

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/qCammel-70-x-AWQ.