What are the hardware requirements for Hy Memory 30B A3B AWQ?

Hy Memory 30B A3B AWQ requires approximately 16.3 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Hy Memory 30B A3B AWQ and how large is it?

Hy Memory 30B A3B AWQ is developed by vinnipukh, a model with 30b 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 Hy Memory 30B A3B AWQ?

Hy Memory 30B A3B AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Hy Memory 30B A3B AWQ by vinnipukh — VRAM 16.3GB, 256K context

Name: Hy Memory 30B A3B AWQ
Author: vinnipukh

Hy Memory 30B A3B AWQ is an open-source language model by vinnipukh. Features: 30b LLM, VRAM: 16.3GB, Context: 256K, License: apache-2.0, Quantized.

Arxiv:2610.22196 Agent-memory Awq Base model:quantized:tencent/h... Base model:tencent/hy-memory-3... Compressed-tensors Conversational En Hunyuan Hy-memory Hy v3 Int4 Llm-compressor Long-term-memory Mem0 Memory Memory-extraction Mixture-of-experts Moe Quantized Region:us Safetensors Tencent Vllm Zh

Model Card on HF 🤗: https://huggingface.co/vinnipukh/Hy-Memory-30B-A3B-AWQ

Hy Memory 30B A3B AWQ Parameters and Internals

LLM Name	Hy Memory 30B A3B AWQ
Repository 🤗	https://huggingface.co/vinnipukh/Hy-Memory-30B-A3B-AWQ
Base Model(s)	Hy Memory 30B A3B tencent/Hy-Memory-30B-A3B
Model Size	30b
Required VRAM	16.3 GB
Updated	2026-10-22
Maintainer	vinnipukh
Model Type	hy_v3
Model Files	16.3 GB
Supported Languages	en zh
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	HYV3ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.17.0
Tokenizer Class	TokenizersBackend
Padding Token	<｜hy_▁pad▁｜>
Vocabulary Size	120832

Rank the Hy Memory 30B A3B AWQ 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 Hy Memory 30B A3B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Hy Memory 30B A3B MLX 4bit	256K / 17 GB	157	2
Hy Memory 30B A3B	256K / 50.5 GB	2145	242
Hy MT2 30B A3B	256K / 48 GB	178301	484
Hy Memory 30B A3B Exl3 4.08bpw	256K / 16 GB	150	1
Hy Memory 30B A3B FP8	256K / 25.1 GB	360	13

Note: green Score (e.g. "73.2") means that the model is better than vinnipukh/Hy-Memory-30B-A3B-AWQ.