What are the hardware requirements for Amber AWQ?

Amber AWQ requires approximately 3.9 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 Amber AWQ and how large is it?

Amber AWQ is developed by TheBloke, a model with 6.7b 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 Amber AWQ?

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

Amber AWQ by TheBloke — VRAM 3.9GB, 2K context

Name: Amber AWQ
Author: TheBloke

Amber AWQ is an open-source language model by TheBloke. Features: 6.7b LLM, VRAM: 3.9GB, Context: 2K, License: apache-2.0, Quantized, LLM Explorer Score: 0.1.

4-bit Awq Base model:llm360/amber Base model:quantized:llm360/am... En Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/Amber-AWQ

Amber AWQ Parameters and Internals

Model Type

amber, text-generation

Additional Notes

Amber is a 7B English language model with LLaMA architecture, aiming for comprehensive and open-sourced LLM development.

Supported Languages

English (primary)

Training Details

Data Sources:

Arxiv, Book, C4, Refined-Web, StarCoder, StackExchange, Wikipedia

Data Volume:

1259.13 billion tokens

Context Length:

2048

Model Architecture:

LLaMA-7B architecture

Input Output

Input Format:

{prompt}

Accepted Modalities:

text

Output Format:

Text-based response according to the input

LLM Name	Amber AWQ
Repository 🤗	https://huggingface.co/TheBloke/Amber-AWQ
Model Name	Amber
Model Creator	LLM360
Base Model(s)	Amber LLM360/Amber
Model Size	6.7b
Required VRAM	3.9 GB
Updated	2026-05-04
Maintainer	TheBloke
Model Type	amber
Model Files	3.9 GB
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.36.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Amber 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 Amber AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...epseek Coder 6.7B Instruct AWQ	16K / 3.9 GB	291702	19
Deepseek Coder 6.7B Base AWQ	16K / 3.9 GB	16513	10
Wavecoder Ultra 1.1 6.7B AWQ	16K / 3.9 GB	6	0
Wavecoder Ultra 1.1 6.7B AWQ	16K / 3.9 GB	11	0
Magicoder S DS 6.7B AWQ	16K / 3.9 GB	8	9
Deepseek Coder 6.7B Base AWQ	16K / 3.9 GB	0	0
Law Chat AWQ	4K / 3.9 GB	7	4
Finance Chat AWQ	4K / 3.9 GB	7	3
Medicine Chat AWQ	4K / 3.9 GB	3	3
AdaptLLM Finance Chat AWQ	4K / 3.9 GB	0	1

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