What are the hardware requirements for Miquella 120B?

Miquella 120B requires approximately 235.6 GB of VRAM and supports a context window of 31K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Miquella 120B and how large is it?

Miquella 120B is developed by alpindale, 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 Miquella 120B?

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

Miquella 120B by alpindale — VRAM 235.6GB, 31K context

Name: Miquella 120B
Author: alpindale

Miquella 120B is an open-source language model by alpindale. Features: 120b LLM, VRAM: 235.6GB, Context: 31K, LLM Explorer Score: 0.11.

Endpoints compatible Llama Merge Mergekit Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/alpindale/miquella-120b

Miquella 120B Parameters and Internals

Additional Notes

Model is a merge of pre-trained language models using mergekit.

LLM Name	Miquella 120B
Repository 🤗	https://huggingface.co/alpindale/miquella-120b
Model Size	120b
Required VRAM	235.6 GB
Updated	2026-08-01
Maintainer	alpindale
Model Type	llama
Model Files	9.7 GB: 1-of-24 9.8 GB: 2-of-24 9.8 GB: 3-of-24 9.8 GB: 4-of-24 9.9 GB: 5-of-24 9.8 GB: 6-of-24 10.0 GB: 7-of-24 9.8 GB: 8-of-24 9.8 GB: 9-of-24 9.7 GB: 10-of-24 9.8 GB: 11-of-24 9.6 GB: 12-of-24 9.8 GB: 13-of-24 10.0 GB: 14-of-24 9.8 GB: 15-of-24 9.8 GB: 16-of-24 10.0 GB: 17-of-24 9.8 GB: 18-of-24 9.7 GB: 19-of-24 9.9 GB: 20-of-24 10.0 GB: 21-of-24 9.8 GB: 22-of-24 9.8 GB: 23-of-24 9.7 GB: 24-of-24
Model Architecture	LlamaForCausalLM
Context Length	32764
Model Max Length	32764
Transformers Version	4.37.1
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Miquella 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 Miquella 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
...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
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 alpindale/miquella-120b.