What are the hardware requirements for Q38fn Heretic2 Mxfp4 Fp8?

Q38fn Heretic2 Mxfp4 Fp8 requires approximately 125.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Q38fn Heretic2 Mxfp4 Fp8 and how large is it?

Q38fn Heretic2 Mxfp4 Fp8 is developed by davetha, a model with 180b 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 Q38fn Heretic2 Mxfp4 Fp8?

Q38fn Heretic2 Mxfp4 Fp8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Q38fn Heretic2 Mxfp4 Fp8 by davetha — VRAM 125.8GB

Name: Q38fn Heretic2 Mxfp4 Fp8
Author: davetha

Q38fn Heretic2 Mxfp4 Fp8 is an open-source language model by davetha. Features: 180b LLM, VRAM: 125.8GB, License: other, LLM Explorer Score: 0.28.

8-bit Abliterated Compressed-tensors Conversational Decensored Endpoints compatible Heretic Image-text-to-text Qwen4 exp Region:us Reproducible Safetensors Sharded Tensorflow Uncensored

Model Card on HF 🤗: https://huggingface.co/davetha/q38fn-heretic2-mxfp4-fp8

Q38fn Heretic2 Mxfp4 Fp8 Parameters and Internals

LLM Name	Q38fn Heretic2 Mxfp4 Fp8
Repository 🤗	https://huggingface.co/davetha/q38fn-heretic2-mxfp4-fp8
Model Size	180b
Required VRAM	125.8 GB
Updated	2026-09-19
Maintainer	davetha
Model Type	qwen4_exp
Model Files	5.3 GB: 1-of-25 5.2 GB: 2-of-25 5.2 GB: 3-of-25 5.2 GB: 4-of-25 5.2 GB: 5-of-25 5.2 GB: 6-of-25 5.2 GB: 7-of-25 5.2 GB: 8-of-25 5.2 GB: 9-of-25 5.2 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 3.7 GB: 25-of-25
Model Architecture	Qwen4ExpForConditionalGeneration
License	other
Model Max Length	262144
Transformers Version	5.16.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Q38fn Heretic2 Mxfp4 Fp8 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 Q38fn Heretic2 Mxfp4 Fp8

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 Flash Next	0K / 129.5 GB	4810	3918
Qwen3.8 Flash Next FP8	0K / 65.7 GB	2219	117
Qwen3.8 Flash Next W4A16	0K / 0.5 GB	6043	22
Qwen3.8 Flash Next FP8	0K / 65.7 GB	185	30
Qwen3.8 Flash Next Nota NVFP4	0K / 18.7 GB	196	20
...Next Dynamic OQ5e BF16 PLE Mtp	0K / 187.1 GB	233	2
Qwen3.8 Flash Next W4A16	0K / 0.5 GB	541	6
...3.8 Flash Next ABLITERATED FP8	0K / 64.7 GB	254	6
... Flash Next Heretic 2 OQ4e Mtp	0K / 106.4 GB	315	1
...en3.8 Flash Next DERISKED BF16	0K / 129.5 GB	231	4

Note: green Score (e.g. "73.2") means that the model is better than davetha/q38fn-heretic2-mxfp4-fp8.