What are the hardware requirements for Chat Goliath 120B 80K?

Chat Goliath 120B 80K requires approximately 236.3 GB of VRAM and supports a context window of 80K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Chat Goliath 120B 80K and how large is it?

Chat Goliath 120B 80K is developed by hongyin, a model with 120b 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 Chat Goliath 120B 80K?

Chat Goliath 120B 80K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Chat Goliath 120B 80K by hongyin — VRAM 236.3GB, 80K context

Name: Chat Goliath 120B 80K
Author: hongyin

Chat Goliath 120B 80K is an open-source language model by hongyin. Features: 120b LLM, VRAM: 236.3GB, Context: 80K, LLM Explorer Score: 0.1.

Arxiv:2312.14480 En Endpoints compatible Llama Pytorch Region:us Sharded Zh

Model Card on HF 🤗: https://huggingface.co/hongyin/chat-goliath-120b-80k

Chat Goliath 120B 80K Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

conversation assistance

Applications:

English-Chinese conversation

Primary Use Cases:

language translation, multilingual text generation

Additional Notes

The customized vocabulary better supports Chinese.

Supported Languages

English (full), Chinese (extended)

Training Details

Methodology:

instruction fine-tuning

Input Output

Accepted Modalities:

text

Performance Tips:

Users are encouraged to continue fine-tuning instructions to improve QA capabilities.

LLM Name	Chat Goliath 120B 80K
Repository 🤗	https://huggingface.co/hongyin/chat-goliath-120b-80k
Model Size	120b
Required VRAM	236.3 GB
Updated	2026-08-01
Maintainer	hongyin
Model Type	llama
Model Files	9.7 GB: 1-of-24 10.0 GB: 2-of-24 9.8 GB: 3-of-24 9.8 GB: 4-of-24 9.8 GB: 5-of-24 10.0 GB: 6-of-24 9.8 GB: 7-of-24 9.8 GB: 8-of-24 9.8 GB: 9-of-24 10.0 GB: 10-of-24 9.8 GB: 11-of-24 9.8 GB: 12-of-24 9.8 GB: 13-of-24 10.0 GB: 14-of-24 9.8 GB: 15-of-24 9.8 GB: 16-of-24 9.8 GB: 17-of-24 10.0 GB: 18-of-24 9.8 GB: 19-of-24 9.8 GB: 20-of-24 9.8 GB: 21-of-24 10.0 GB: 22-of-24 9.8 GB: 23-of-24 9.8 GB: 24-of-24
Supported Languages	en zh
Model Architecture	LlamaForCausalLM
Context Length	81920
Model Max Length	81920
Transformers Version	4.34.0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	49300
Torch Data Type	bfloat16

Rank the Chat Goliath 120B 80K 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 Chat Goliath 120B 80K

Best Alternatives	Context / RAM	Downloads	Likes
Electric Sheep 120B	31K / 238.8 GB	5	0
QueenLiz 120B	31K / 240.9 GB	5	3
Miquella 120B	31K / 235.6 GB	48	22
...ma 3 Instruct 120B Cat A Llama	8K / 243.9 GB	2	1
Meta Llama 3 225B Instruct	8K / 443.2 GB	274	18
...0B Instruct Abliterated Merged	8K / 243.7 GB	1	1
Colossus 120b	4K / 207 GB	5	1
Megamarcoroni 120B	4K / 212 GB	50	0
Mlx Community Goliath 120B	4K / 234 GB	0	2
Ultra WizardLM 120B V0.1	4K / 240.5 GB	4	2

Note: green Score (e.g. "73.2") means that the model is better than hongyin/chat-goliath-120b-80k.