What are the hardware requirements for WinterGoliath 123B GPTQ?

WinterGoliath 123B GPTQ requires approximately 62.8 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed WinterGoliath 123B GPTQ and how large is it?

WinterGoliath 123B GPTQ is developed by TheBloke, a model with 123b 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 WinterGoliath 123B GPTQ?

WinterGoliath 123B GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

WinterGoliath 123B GPTQ by TheBloke — VRAM 62.8GB, 4K context

Name: WinterGoliath 123B GPTQ
Author: TheBloke

WinterGoliath 123B GPTQ is an open-source language model by TheBloke. Features: 123b LLM, VRAM: 62.8GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.1.

4-bit Base model:chuckmcsneed/winter... Base model:quantized:chuckmcsn... Gptq Llama Merge Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheBloke/WinterGoliath-123b-GPTQ

WinterGoliath 123B GPTQ Parameters and Internals

Model Type

llama

Additional Notes

This model is a merge of Xwin and WinterGoddess, utilizing mergekit. It appears to show slightly improved performance in NeoEvalPlusN_benchmark tests compared to Goliath and has been observed to perform better in the Kanye Test.

Input Output

Input Format:

{prompt}

LLM Name	WinterGoliath 123B GPTQ
Repository 🤗	https://huggingface.co/TheBloke/WinterGoliath-123b-GPTQ
Model Name	WinterGoliath 123B
Model Creator	Charles McSneed
Base Model(s)	WinterGoliath 123B ChuckMcSneed/WinterGoliath-123b
Model Size	123b
Required VRAM	62.8 GB
Updated	2026-07-28
Maintainer	TheBloke
Model Type	llama
Model Files	49.0 GB: 1-of-2 13.8 GB: 2-of-2
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the WinterGoliath 123B GPTQ 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 WinterGoliath 123B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
DoubleGold V0.1 123B 32K	32K / 247.7 GB	35	1
Premerge XE XE 123B	4K / 247.5 GB	22	1
Premerge EX EX 123B	4K / 247.5 GB	19	1
WinterGoliath 123B	4K / 247.5 GB	69	7
WinterGoliath 123B AWQ	4K / 65 GB	3	2
Dicephal 123B	4K / 247.7 GB	19	5

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/WinterGoliath-123b-GPTQ.