What are the hardware requirements for Megamarcoroni 120B?

Megamarcoroni 120B requires approximately 212 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 Megamarcoroni 120B and how large is it?

Megamarcoroni 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.

How does Megamarcoroni 120B perform on standard benchmarks?

Megamarcoroni 120B has the following published scores: MMLU 69.88. Compare against reference models on this page or on the LLM Explorer leaderboards.

Megamarcoroni 120B by ibivibiv — VRAM 212GB, 4K context

Name: Megamarcoroni 120B
Author: ibivibiv

Megamarcoroni 120B is an open-source language model by ibivibiv. Features: 120b LLM, VRAM: 212GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.13, Arc: 72, HellaSwag: 88.9, MMLU: 69.9, GSM8K: 21.5.

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

Model Card on HF 🤗: https://huggingface.co/ibivibiv/megamarcoroni-120b

Megamarcoroni 120B Parameters and Internals

Model Type

text-generation

Additional Notes

The model was removed previously and is now re-evaluated. Known as '2x70B Marcoroni'.

LLM Name	Megamarcoroni 120B
Repository 🤗	https://huggingface.co/ibivibiv/megamarcoroni-120b
Model Size	120b
Required VRAM	212 GB
Updated	2026-08-01
Maintainer	ibivibiv
Model Type	llama
Model Files	4.8 GB: 1-of-106 4.6 GB: 2-of-106 4.4 GB: 3-of-106 5.0 GB: 4-of-106 4.4 GB: 5-of-106 4.4 GB: 6-of-106 5.0 GB: 7-of-106 4.4 GB: 8-of-106 4.4 GB: 9-of-106 5.0 GB: 10-of-106 4.4 GB: 11-of-106 4.4 GB: 12-of-106 5.0 GB: 13-of-106 4.4 GB: 14-of-106 4.4 GB: 15-of-106 5.0 GB: 16-of-106 4.4 GB: 17-of-106 4.4 GB: 18-of-106 5.0 GB: 19-of-106 4.4 GB: 20-of-106 4.4 GB: 21-of-106 5.0 GB: 22-of-106 4.4 GB: 23-of-106 4.4 GB: 24-of-106 5.0 GB: 25-of-106 4.4 GB: 26-of-106 4.4 GB: 27-of-106 5.0 GB: 28-of-106 4.4 GB: 29-of-106 4.4 GB: 30-of-106 5.0 GB: 31-of-106 4.4 GB: 32-of-106 4.4 GB: 33-of-106 5.0 GB: 34-of-106 4.4 GB: 35-of-106 4.4 GB: 36-of-106 5.0 GB: 37-of-106 4.4 GB: 38-of-106 4.4 GB: 39-of-106 5.0 GB: 40-of-106 4.4 GB: 41-of-106 4.4 GB: 42-of-106 5.0 GB: 43-of-106 4.4 GB: 44-of-106 4.4 GB: 45-of-106 5.0 GB: 46-of-106
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 Megamarcoroni 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 Megamarcoroni 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
Colossus 120b	4K / 207 GB	5	1
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/megamarcoroni-120b.