LLM EXPLORER 59,516 MODELS INDEXED

AquilaChat2 34B 16K AWQ by TheBloke

By TheBloke · 10 downloads
HF Repo ↗ Copy URL

AquilaChat2 34B 16K AWQ is an open-source language model by TheBloke. Features: 34b LLM, VRAM: 19.3GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.09.

  4-bit   Aquila   Awq Base model:baai/aquilachat2-34... Base model:quantized:baai/aqui...   Custom code   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/AquilaChat2-34B-16K-AWQ 

AquilaChat2 34B 16K AWQ Parameters and Internals

Model Type 
aquila
Input Output 
Input Format:
Human: {prompt} Assistant:
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
1.2
Date:
2023-10-25
Notes:
Improved long-text synthesis capabilities, approaching GPT-3.5-16K level. Enhanced performance in non-long-text scenarios through additional conventional instruction fine-tuning corpora.
LLM NameAquilaChat2 34B 16K AWQ
Repository 🤗https://huggingface.co/TheBloke/AquilaChat2-34B-16K-AWQ 
Model NameAquilachat2 34B 16K
Model CreatorBeijing Academy of Artificial Intelligence
Base Model(s)  AquilaChat2 34B 16K   BAAI/AquilaChat2-34B-16K
Model Size34b
Required VRAM19.3 GB
Updated2026-08-07
MaintainerTheBloke
Model Typeaquila
Model Files  10.0 GB: 1-of-2   9.3 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureAquilaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size100008
Torch Data Typefloat16

Best Alternatives to AquilaChat2 34B 16K AWQ

Best Alternatives
Context / RAM
Downloads
Likes
AquilaChat2 34B AWQ4K / 19.3 GB61
AquilaChat2 34B 16K16K / 67.2 GB16826
Aquila2 34B8K / 136.4 GB31219
AquilaChat2 34B4K / 67.2 GB14847
AquilaChat2 34B 16K GPTQ4K / 18.7 GB75
AquilaChat2 34B GPTQ4K / 18.7 GB162
H2ogpt 16K Aquilachat2 34B4K / 67.2 GB94
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/AquilaChat2-34B-16K-AWQ.