What are the hardware requirements for Colossus 120B?

Colossus 120B requires approximately 207 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 Colossus 120B and how large is it?

Colossus 120B is developed by ibivibiv, 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 Colossus 120B?

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

Colossus 120B by ibivibiv — VRAM 207GB, 4K context

Name: Colossus 120B
Author: ibivibiv

Colossus 120B is an open-source language model by ibivibiv. Features: 120b LLM, VRAM: 207GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.19.

Arxiv:1910.09700 En Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ibivibiv/colossus_120b

Colossus 120B Parameters and Internals

LLM Name	Colossus 120b
Repository 🤗	https://huggingface.co/ibivibiv/colossus_120b
Model Size	120b
Required VRAM	207 GB
Updated	2026-08-03
Maintainer	ibivibiv
Model Type	llama
Model Files	4.8 GB: 1-of-104 4.6 GB: 2-of-104 4.4 GB: 3-of-104 5.0 GB: 4-of-104 4.4 GB: 5-of-104 4.4 GB: 6-of-104 5.0 GB: 7-of-104 4.4 GB: 8-of-104 4.4 GB: 9-of-104 5.0 GB: 10-of-104 4.4 GB: 11-of-104 4.4 GB: 12-of-104 5.0 GB: 13-of-104 4.4 GB: 14-of-104 4.4 GB: 15-of-104 5.0 GB: 16-of-104 4.4 GB: 17-of-104 4.4 GB: 18-of-104 5.0 GB: 19-of-104 4.4 GB: 20-of-104 4.4 GB: 21-of-104 5.0 GB: 22-of-104 4.4 GB: 23-of-104 4.4 GB: 24-of-104 5.0 GB: 25-of-104 4.4 GB: 26-of-104 4.4 GB: 27-of-104 5.0 GB: 28-of-104 4.4 GB: 29-of-104 4.4 GB: 30-of-104 5.0 GB: 31-of-104 4.4 GB: 32-of-104 4.4 GB: 33-of-104 5.0 GB: 34-of-104 4.4 GB: 35-of-104 4.4 GB: 36-of-104 5.0 GB: 37-of-104 4.4 GB: 38-of-104 4.4 GB: 39-of-104 5.0 GB: 40-of-104 4.4 GB: 41-of-104 4.4 GB: 42-of-104 5.0 GB: 43-of-104 4.4 GB: 44-of-104 4.4 GB: 45-of-104
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.2
Vocabulary Size	32000
Torch Data Type	float32

Rank the Colossus 120B 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 Colossus 120B

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
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 ibivibiv/colossus_120b.