What are the hardware requirements for Amber?

Amber requires approximately 13.5 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 Amber and how large is it?

Amber is developed by LLM360, 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.

How does Amber perform on standard benchmarks?

Amber has the following published scores: MMLU 26.84. Compare against reference models on this page or on the LLM Explorer leaderboards.

Amber by LLM360 — VRAM 13.5GB, 2K context

Name: Amber
Author: LLM360

Amber is an open-source language model by LLM360. Features: 6.7b LLM, VRAM: 13.5GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.15, Arc: 41, HellaSwag: 73.8, MMLU: 26.8, GSM8K: 2.8.

Arxiv:2312.06550 Deploy:azure En Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LLM360/Amber

Amber Parameters and Internals

Model Type

Language model, text generation

Use Cases

Areas:

Research, Commercial applications

Limitations:

Not a SOTA model

Considerations:

Amber is released to make LLM training knowledge accessible to all.

Additional Notes

360 checkpoints available. To download other checkpoints, change the branch from 'main' to the checkpoint you want.

Supported Languages

English (NLP)

Training Details

Data Sources:

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

Data Volume:

1259.13 Billion tokens

Methodology:

Same architecture as LLaMA

Context Length:

2048

Model Architecture:

LLaMA architecture

Input Output

Accepted Modalities:

text

LLM Name	Amber
Repository 🤗	https://huggingface.co/LLM360/Amber
Model Size	6.7b
Required VRAM	13.5 GB
Updated	2026-05-09
Maintainer	LLM360
Model Type	llama
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 3.6 GB: 3-of-3
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Amber 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

Quantized Models of the Amber

Model	Likes	Downloads	VRAM
Amber GGUF	2	245	2 GB
Amber AWQ	1	7	3 GB
Amber GPTQ	1	2	3 GB

Best Alternatives to Amber

Best Alternatives	Context / RAM	Downloads	Likes
Gptnoise37	128K / 13.5 GB	67	0
...Deepseek Coder 6.7B Energy Sft	16K / 13.5 GB	261	0
Deepseek Coder 6.7B Base	16K / 13.5 GB	54216	124
Speechless Coder Ds 6.7B	16K / 13.5 GB	459	7
...ir8 Ds Coder6.7b Rmsprop Iter4	16K / 13.5 GB	183	0
...s Coder6.7b Reflct Adamw Iter2	16K / 13.5 GB	480	0
...ir8 Ds Coder6.7b Rmsprop Iter2	16K / 13.5 GB	183	0
...s Coder6.7b Reflct Adamw Iter1	16K / 13.5 GB	475	0
...ir8 Ds Coder6.7b Rmsprop Iter3	16K / 13.5 GB	165	0
...s Coder6.7b Reflct Adamw Iter3	16K / 13.5 GB	430	0

Note: green Score (e.g. "73.2") means that the model is better than LLM360/Amber.