What are the hardware requirements for Comet 60B A12B BF16?

Comet 60B A12B BF16 requires approximately 122.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Comet 60B A12B BF16 and how large is it?

Comet 60B A12B BF16 is developed by MultiverseComputingCAI, a model with 60b 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 Comet 60B A12B BF16?

Comet 60B A12B BF16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Comet 60B A12B BF16 by MultiverseComputingCAI — VRAM 122.3GB

Name: Comet 60B A12B BF16
Author: MultiverseComputingCAI

Comet 60B A12B BF16 is an open-source language model by MultiverseComputingCAI. Features: 60b LLM, VRAM: 122.3GB, License: other, LLM Explorer Score: 0.33.

Conversational Custom code En Endpoints compatible Image-text-to-text Nemotron h omni Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/MultiverseComputingCAI/Comet_60B_A12B_BF16

Comet 60B A12B BF16 Parameters and Internals

LLM Name	Comet 60B A12B BF16
Repository 🤗	https://huggingface.co/MultiverseComputingCAI/Comet_60B_A12B_BF16
Base Model(s)	Nemotron-3.5-Super-VL /Nemotron-3.5-Super-VL
Model Size	60b
Required VRAM	122.3 GB
Updated	2026-10-20
Maintainer	MultiverseComputingCAI
Model Type	nemotron_h_omni
Model Files	5.0 GB: 1-of-25 5.0 GB: 2-of-25 5.0 GB: 3-of-25 5.0 GB: 4-of-25 5.0 GB: 5-of-25 5.0 GB: 6-of-25 5.0 GB: 7-of-25 5.0 GB: 8-of-25 5.0 GB: 9-of-25 5.0 GB: 10-of-25 5.0 GB: 11-of-25 5.0 GB: 12-of-25 5.0 GB: 13-of-25 5.0 GB: 14-of-25 5.0 GB: 15-of-25 5.0 GB: 16-of-25 5.0 GB: 17-of-25 5.0 GB: 18-of-25 5.0 GB: 19-of-25 5.0 GB: 20-of-25 5.0 GB: 21-of-25 5.0 GB: 22-of-25 5.0 GB: 23-of-25 5.0 GB: 24-of-25 2.3 GB: 25-of-25 0.0 GB
Supported Languages	en
Model Architecture	NemotronH_Omni_Reasoning_V3
License	other
Model Max Length	262144
Transformers Version	5.12.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|im_end\|>

Rank the Comet 60B A12B BF16 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 Comet 60B A12B BF16

Best Alternatives	Context / RAM	Downloads	Likes
Comet 60B A12B NVFP4	0K / 19 GB	153	6
Comet 60B A12B FP8	0K / 28.4 GB	27	1