LLM EXPLORER 57,252 MODELS INDEXED

Amber GPTQ by TheBloke

By TheBloke · 2 downloads
HF Repo ↗ Copy URL

Amber GPTQ 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   Base model:llm360/amber Base model:quantized:llm360/am...   En   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Amber-GPTQ 

Amber GPTQ Parameters and Internals

Model Type 
text-generation, language model
Supported Languages 
en (English)
Training Details 
Data Sources:
Arxiv, Book, C4, Refined-Web, StarCoder, StackExchange, Wikipedia
Data Volume:
1259.13 billion tokens
Context Length:
2048
Model Architecture:
LLaMA architecture with 32 hidden layers, 11008 intermediate size (MLPs), 32 attention heads.
Input Output 
Input Format:
{prompt}
Accepted Modalities:
text
LLM NameAmber GPTQ
Repository 🤗https://huggingface.co/TheBloke/Amber-GPTQ 
Model NameAmber
Model CreatorLLM360
Base Model(s)  Amber   LLM360/Amber
Model Size6.7b
Required VRAM3.9 GB
Updated2026-07-31
MaintainerTheBloke
Model Typeamber
Model Files  3.9 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.36.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Amber GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...pseek Coder 6.7B Instruct GPTQ16K / 3.9 GB51425
Magicoder S DS 6.7B GPTQ16K / 3.9 GB77
Deepseek Coder 6.7B Base GPTQ16K / 3.9 GB205
Medicine Chat GPTQ4K / 3.9 GB206
Law Chat GPTQ4K / 3.9 GB54
Finance Chat GPTQ4K / 3.9 GB43
Gorilla Openfunctions V1 GPTQ4K / 3.9 GB75
Llama Tagger HF GPTQ 4bits2K / 3.9 GB80
...lliott Chinese LLaMa GPTQ V1.02K / 13.5 GB520
Elliott Chinese LLaMa GPTQ2K / 13.5 GB600
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Amber-GPTQ.