What are the hardware requirements for LFM 2.5 2.6B Heretic?

LFM 2.5 2.6B Heretic requires approximately 5.4 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 LFM 2.5 2.6B Heretic and how large is it?

LFM 2.5 2.6B Heretic is developed by heretic-org, a model with 2.6b 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 LFM 2.5 2.6B Heretic?

LFM 2.5 2.6B Heretic is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM 2.5 2.6B Heretic by heretic-org — VRAM 5.4GB, 128K context

Name: LFM 2.5 2.6B Heretic
Author: heretic-org

LFM 2.5 2.6B Heretic is an open-source language model by heretic-org. Features: 2.6b LLM, VRAM: 5.4GB, Context: 128K, License: other, LLM Explorer Score: 0.33.

Arxiv:2511.23404 Abliterated Ar Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-2.6... Conversational De Decensored Edge En Endpoints compatible Es Fr Heretic Hi Id It Ja Ko Lfm2 Lfm2.5 Liquid Pl Pt Region:us Reproducible Ru Safetensors Sharded Tensorflow Th Uncensored Vi Zh

Model Card on HF 🤗: https://huggingface.co/heretic-org/LFM-2.5-2.6B-heretic

LFM 2.5 2.6B Heretic Parameters and Internals

LLM Name	LFM 2.5 2.6B Heretic
Repository 🤗	https://huggingface.co/heretic-org/LFM-2.5-2.6B-heretic
Base Model(s)	LiquidAI/LFM2.5-2.6B LiquidAI/LFM2.5-2.6B
Model Size	2.6b
Required VRAM	5.4 GB
Updated	2026-08-13
Maintainer	heretic-org
Model Type	lfm2
Model Files	5.0 GB: 1-of-2 0.4 GB: 2-of-2
Supported Languages	ar zh en fr de hi id it ja ko pl pt ru es th vi
Model Architecture	Lfm2ForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	5.14.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the LFM 2.5 2.6B Heretic 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 LFM 2.5 2.6B Heretic

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 2.6B	128K / 5.4 GB	81522	398
...max Video Prompt Enhancer 2.6B	128K / 5.4 GB	229	1
Lfm2.5 2.6B Manumit V1	128K / 5.4 GB	354	0
LFM2.5 2.6B MLX Bf16	128K / 5.3 GB	108	2
LFM2.5 2.6B MLX Mxfp4	128K / 1.6 GB	57	2
LFM2.5 2.6B MLX Nvfp4	128K / 1.6 GB	64	1
LFM2.5 2.6B MLX Mxfp8	128K / 2.8 GB	23	1
LFM2.5 2.6B Base	125K / 5.4 GB	809	37
LFM2.5 2.6B ONNX	125K / GB	1900	18
Macaw	125K / 5.4 GB	691	6

Note: green Score (e.g. "73.2") means that the model is better than heretic-org/LFM-2.5-2.6B-heretic.