What are the hardware requirements for Gravity 16B A3B Preview?

Gravity 16B A3B Preview requires approximately 32.5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gravity 16B A3B Preview and how large is it?

Gravity 16B A3B Preview is developed by trillionlabs, a model with 16b 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 Gravity 16B A3B Preview?

Gravity 16B A3B Preview is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gravity 16B A3B Preview by trillionlabs — VRAM 32.5GB, 128K context

Name: Gravity 16B A3B Preview
Author: trillionlabs

Gravity 16B A3B Preview is an open-source language model by trillionlabs. Features: 16b LLM, VRAM: 32.5GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.26.

Base model:finetune:trillionla... Base model:trillionlabs/gravit... Chat Conversational Custom code En Gravity Gravity moe Ko Mixture-of-experts Moe Post-trained Preview Region:us Safetensors Sharded Tensorflow Trillion-labs

Model Card on HF 🤗: https://huggingface.co/trillionlabs/Gravity-16B-A3B-Preview

Gravity 16B A3B Preview Parameters and Internals

LLM Name	Gravity 16B A3B Preview
Repository 🤗	https://huggingface.co/trillionlabs/Gravity-16B-A3B-Preview
Base Model(s)	Gravity 16B A3B Base trillionlabs/Gravity-16B-A3B-Base
Model Size	16b
Required VRAM	32.5 GB
Updated	2026-08-05
Maintainer	trillionlabs
Model Type	deepseek_v3
Model Files	5.0 GB: 1-of-7 5.0 GB: 2-of-7 5.0 GB: 3-of-7 5.0 GB: 4-of-7 5.0 GB: 5-of-7 5.0 GB: 6-of-7 2.5 GB: 7-of-7
Supported Languages	en ko
Model Architecture	DeepseekV3ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.57.6
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|begin_of_video\|>
Vocabulary Size	151552

Rank the Gravity 16B A3B Preview 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 Gravity 16B A3B Preview

Best Alternatives	Context / RAM	Downloads	Likes
Mnl	128K / 32.6 GB	5	0
Moonlight 16B A3B Instruct	8K / 32.6 GB	45597	196
Moonlight 16B A3B	8K / 32.6 GB	11091	115
...3B Instruct Abliterated Pruned	8K / 17.5 GB	81	6
...onlight 16B A3B Instruct 4 Bit	8K / 9 GB	136	4
...t 16B A3B Instruct Abliterated	8K / 31.9 GB	16	8