What are the hardware requirements for Aquif 3 MoE 17B A2.8B?

Aquif 3 MoE 17B A2.8B requires approximately 33.6 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Aquif 3 MoE 17B A2.8B and how large is it?

Aquif 3 MoE 17B A2.8B is developed by aquiffoo, a model with 16.8b 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 Aquif 3 MoE 17B A2.8B?

Aquif 3 MoE 17B A2.8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Aquif 3 MoE 17B A2.8B by aquiffoo — VRAM 33.6GB, 32K context

Name: Aquif 3 MoE 17B A2.8B
Rating: 4 (8 reviews)
Author: aquiffoo

Aquif 3 MoE 17B A2.8B is an open-source language model by aquiffoo. Features: 16.8b LLM, VRAM: 33.6GB, Context: 32K, License: apache-2.0, MoE, LLM Explorer Score: 0.19.

17b Aquif moe Autotrain compatible Bailing-like Base model:finetune:inclusiona... Base model:inclusionai/ling-li... Code Conversational Custom code En Language Math Moe Qwen-like Region:us Safetensors Science Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/aquiffoo/aquif-3-moe-17b-a2.8b

Aquif 3 MoE 17B A2.8B Parameters and Internals

LLM Name	Aquif 3 MoE 17B A2.8B
Repository 🤗	https://huggingface.co/aquiffoo/aquif-3-moe-17b-a2.8b
Base Model(s)	Ling Lite Base inclusionAI/Ling-lite-base
Model Size	16.8b
Required VRAM	33.6 GB
Updated	2025-09-02
Maintainer	aquiffoo
Model Type	aquif_moe
Model Files	10.0 GB: 1-of-4 10.0 GB: 2-of-4 10.0 GB: 3-of-4 3.6 GB: 4-of-4
Supported Languages	en
Model Architecture	AquifMoeForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.53.1
Tokenizer Class	PreTrainedTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	126464
Torch Data Type	bfloat16

Rank the Aquif 3 MoE 17B A2.8B 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 Aquif 3 MoE 17B A2.8B

Best Alternatives	Context / RAM	Downloads	Likes
Aquif 3 MoE 17B A2.8B	32K / 33.6 GB	19	14

Note: green Score (e.g. "73.2") means that the model is better than aquiffoo/aquif-3-moe-17b-a2.8b.