LLM EXPLORER 59,516 MODELS INDEXED

AquilaChat2 34B 16K by BAAI

By BAAI · 168 downloads
HF Repo ↗ Copy URL

AquilaChat2 34B 16K is an open-source language model by BAAI. Features: 34b LLM, VRAM: 67.2GB, Context: 16K, License: other, LLM Explorer Score: 0.09.

  Arxiv:2408.07410   Aquila   Custom code   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/BAAI/AquilaChat2-34B-16K 

AquilaChat2 34B 16K Parameters and Internals

Model Type 
chat, long-text synthesis
Additional Notes 
The additional details of the Aquila model will be presented in the official technical report.
Supported Languages 
en (English), zh (Chinese)
Release Notes 
Version:
v1.2
Date:
2023-10-25
Notes:
Significantly improved long-text synthesis capabilities compared to the V1 version, incorporates more conventional instruction fine-tuning corpora, enhancing performance in non-long-text scenarios compared to the V1 version.
LLM NameAquilaChat2 34B 16K
Repository 🤗https://huggingface.co/BAAI/AquilaChat2-34B-16K 
Model Size34b
Required VRAM67.2 GB
Updated2026-08-24
MaintainerBAAI
Model Typeaquila
Model Files  10.0 GB: 1-of-7   9.8 GB: 2-of-7   9.7 GB: 3-of-7   9.7 GB: 4-of-7   9.7 GB: 5-of-7   9.7 GB: 6-of-7   8.6 GB: 7-of-7
Model ArchitectureAquilaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.31.0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size100008
Torch Data Typebfloat16

Quantized Models of the AquilaChat2 34B 16K

Model
Likes
Downloads
VRAM
AquilaChat2 34B 16K GGUF1249014 GB
AquilaChat2 34B 16K GPTQ5718 GB
AquilaChat2 34B 16K AWQ31019 GB

Best Alternatives to AquilaChat2 34B 16K

Best Alternatives
Context / RAM
Downloads
Likes
Aquila2 34B8K / 136.4 GB31219
AquilaChat2 34B4K / 67.2 GB14847
H2ogpt 16K Aquilachat2 34B4K / 67.2 GB94
AquilaChat2 34B 16K GPTQ4K / 18.7 GB75
AquilaChat2 34B GPTQ4K / 18.7 GB162
AquilaChat2 34B 16K AWQ4K / 19.3 GB103
AquilaChat2 34B AWQ4K / 19.3 GB61
Note: green Score (e.g. "73.2") means that the model is better than BAAI/AquilaChat2-34B-16K.