What are the hardware requirements for Ultra WizardLM 120B V0.1?

Ultra WizardLM 120B V0.1 requires approximately 240.5 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 Ultra WizardLM 120B V0.1 and how large is it?

Ultra WizardLM 120B V0.1 is developed by MaziyarPanahi, 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 Ultra WizardLM 120B V0.1?

Ultra WizardLM 120B V0.1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ultra WizardLM 120B V0.1 by MaziyarPanahi — VRAM 240.5GB, 4K context

Name: Ultra WizardLM 120B V0.1
Author: MaziyarPanahi

Ultra WizardLM 120B V0.1 is an open-source language model by MaziyarPanahi. Features: 120b LLM, VRAM: 240.5GB, Context: 4K, License: agpl-3.0, LLM Explorer Score: 0.11.

Endpoints compatible Llama Merge Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/MaziyarPanahi/Ultra-WizardLM-120B-v0.1

Ultra WizardLM 120B V0.1 Parameters and Internals

LLM Name	Ultra WizardLM 120B V0.1
Repository 🤗	https://huggingface.co/MaziyarPanahi/Ultra-WizardLM-120B-v0.1
Model Size	120b
Required VRAM	240.5 GB
Updated	2026-07-26
Maintainer	MaziyarPanahi
Model Type	llama
Model Files	9.6 GB: 1-of-25 10.0 GB: 2-of-25 9.8 GB: 3-of-25 9.9 GB: 4-of-25 10.0 GB: 5-of-25 9.8 GB: 6-of-25 9.9 GB: 7-of-25 9.8 GB: 8-of-25 9.9 GB: 9-of-25 10.0 GB: 10-of-25 9.7 GB: 11-of-25 9.9 GB: 12-of-25 9.9 GB: 13-of-25 9.8 GB: 14-of-25 10.0 GB: 15-of-25 10.0 GB: 16-of-25 9.7 GB: 17-of-25 9.8 GB: 18-of-25 9.9 GB: 19-of-25 10.0 GB: 20-of-25 9.7 GB: 21-of-25 9.9 GB: 22-of-25 9.6 GB: 23-of-25 9.7 GB: 24-of-25 4.2 GB: 25-of-25
Model Architecture	LlamaForCausalLM
License	agpl-3.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.2
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	32001
Torch Data Type	float16

Rank the Ultra WizardLM 120B V0.1 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 Ultra WizardLM 120B V0.1

Best Alternatives	Context / RAM	Downloads	Likes
Chat Goliath 120B 80K	80K / 236.3 GB	10	1
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

Note: green Score (e.g. "73.2") means that the model is better than MaziyarPanahi/Ultra-WizardLM-120B-v0.1.