What are the hardware requirements for Dicephal 123B?

Dicephal 123B requires approximately 247.7 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 Dicephal 123B and how large is it?

Dicephal 123B is developed by ChuckMcSneed, 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 Dicephal 123B?

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

Dicephal 123B by ChuckMcSneed — VRAM 247.7GB, 4K context

Name: Dicephal 123B
Author: ChuckMcSneed

Dicephal 123B is an open-source language model by ChuckMcSneed. Features: 123b LLM, VRAM: 247.7GB, Context: 4K, License: llama2, LLM Explorer Score: 0.1.

Endpoints compatible Llama Merge Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ChuckMcSneed/Dicephal-123B

Dicephal 123B Parameters and Internals

Use Cases

Primary Use Cases:

storywriting, stylized writing, poems

Additional Notes

The model is described as creative and having a sense of humor. It is said to be disobedient like the base model, but great for storywriting and significantly better than the base model in stylized writing and poems.

LLM Name	Dicephal 123B
Repository 🤗	https://huggingface.co/ChuckMcSneed/Dicephal-123B
Model Size	123b
Required VRAM	247.7 GB
Updated	2026-10-21
Maintainer	ChuckMcSneed
Model Type	llama
Model Files	9.8 GB: 1-of-26 9.8 GB: 2-of-26 9.7 GB: 3-of-26 9.8 GB: 4-of-26 9.8 GB: 5-of-26 9.8 GB: 6-of-26 10.0 GB: 7-of-26 10.0 GB: 8-of-26 9.8 GB: 9-of-26 9.8 GB: 10-of-26 9.8 GB: 11-of-26 9.8 GB: 12-of-26 9.8 GB: 13-of-26 9.8 GB: 14-of-26 10.0 GB: 15-of-26 10.0 GB: 16-of-26 9.8 GB: 17-of-26 9.8 GB: 18-of-26 9.8 GB: 19-of-26 9.8 GB: 20-of-26 9.8 GB: 21-of-26 9.8 GB: 22-of-26 10.0 GB: 23-of-26 9.8 GB: 24-of-26 9.8 GB: 25-of-26 1.8 GB: 26-of-26
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Dicephal 123B 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 Dicephal 123B

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
WinterGoliath 123B GPTQ	4K / 62.8 GB	3	1

Note: green Score (e.g. "73.2") means that the model is better than ChuckMcSneed/Dicephal-123B.