What are the hardware requirements for Athene V2 Chat 4.65bpw H6 EXL2?

Athene V2 Chat 4.65bpw H6 EXL2 requires approximately 44.3 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 Athene V2 Chat 4.65bpw H6 EXL2 and how large is it?

Athene V2 Chat 4.65bpw H6 EXL2 is developed by wolfram, a model with 72b 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 Athene V2 Chat 4.65bpw H6 EXL2?

Athene V2 Chat 4.65bpw H6 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Athene V2 Chat 4.65bpw H6 EXL2 by wolfram — VRAM 44.3GB, 32K context

Name: Athene V2 Chat 4.65bpw H6 EXL2
Author: wolfram

Athene V2 Chat 4.65bpw H6 EXL2 is an open-source language model by wolfram. Features: 72b LLM, VRAM: 44.3GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.15.

Ara Athene Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-72b-in... Chat model Conversational Deu Endpoints compatible Eng Exl2 Fra Instruct Ita Jpn Kor Nexusflow Por Quantized Qwen2 Region:us Rlhf Rus Safetensors Sharded Spa Tensorflow Tha Vie Zho

Model Card on HF 🤗: https://huggingface.co/wolfram/Athene-V2-Chat-4.65bpw-h6-exl2

Athene V2 Chat 4.65bpw H6 EXL2 Parameters and Internals

LLM Name	Athene V2 Chat 4.65bpw H6 EXL2
Repository 🤗	https://huggingface.co/wolfram/Athene-V2-Chat-4.65bpw-h6-exl2
Base Model(s)	Qwen/Qwen2.5-72B-Instruct Qwen/Qwen2.5-72B-Instruct
Model Size	72b
Required VRAM	44.3 GB
Updated	2026-05-26
Maintainer	wolfram
Model Type	qwen2
Instruction-Based	Yes
Model Files	8.5 GB: 1-of-6 8.6 GB: 2-of-6 8.6 GB: 3-of-6 8.4 GB: 4-of-6 8.6 GB: 5-of-6 1.6 GB: 6-of-6
Supported Languages	en
Quantization Type	exl2
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.44.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Athene V2 Chat 4.65bpw H6 EXL2 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 Athene V2 Chat 4.65bpw H6 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
...B Instruct 2.0bpw H Novel EXL2	125K / 23 GB	4	1
Qwen2 72B Instruct 4bit	32K / 40.9 GB	56	2
ECE ILAB Q1	32K / 77.8 GB	15	0
Qwen2.5 72B Instruct Bnb 4bit	32K / 41.4 GB	3509	8
Qwen2.5 72B Instruct 4bit	32K / 40.9 GB	1200	7
Qwen2.5 72B Instruct 8bit	32K / 77.1 GB	614	3
Qwen2 72B Instruct Bpw5.5 EXL2	32K / 51.8 GB	1	1
...struct Mix Calibration 4B EXL2	32K / 38.8 GB	3	2
Qwen2 72B Instruct Bpw4 EXL2	32K / 38.7 GB	5	0
Qwen2 72B Instruct 8bit	32K / 77.1 GB	48	1

Note: green Score (e.g. "73.2") means that the model is better than wolfram/Athene-V2-Chat-4.65bpw-h6-exl2.