What are the hardware requirements for LFM2.5 350M Memory Extractor?

LFM2.5 350M Memory Extractor requires approximately 0.7 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LFM2.5 350M Memory Extractor and how large is it?

LFM2.5 350M Memory Extractor is developed by Jepoxy, a model with 350m 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 LFM2.5 350M Memory Extractor?

LFM2.5 350M Memory Extractor is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 350M Memory Extractor by Jepoxy — VRAM 0.7GB, 125K context

Name: LFM2.5 350M Memory Extractor
Author: Jepoxy

LFM2.5 350M Memory Extractor is an open-source language model by Jepoxy. Features: 350m LLM, VRAM: 0.7GB, Context: 125K, LLM Explorer Score: 0.31.

Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-350... Conversational Dataset:jepoxy/text-to-memory-... En Lfm2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Jepoxy/LFM2.5-350M-Memory-Extractor

LFM2.5 350M Memory Extractor Parameters and Internals

LLM Name	LFM2.5 350M Memory Extractor
Repository 🤗	https://huggingface.co/Jepoxy/LFM2.5-350M-Memory-Extractor
Base Model(s)	LiquidAI/LFM2.5-350M-Base LiquidAI/LFM2.5-350M-Base
Model Size	350m
Required VRAM	0.7 GB
Updated	2026-09-05
Maintainer	Jepoxy
Model Type	lfm2
Model Files	0.7 GB
Supported Languages	en
Model Architecture	Lfm2ForCausalLM
Context Length	128000
Model Max Length	128000
Transformers Version	5.9.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the LFM2.5 350M Memory Extractor 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 LFM2.5 350M Memory Extractor

Best Alternatives	Context / RAM	Downloads	Likes
Minico M1 Preview	125K / 0.8 GB	473	1
LFM2.5 350M	125K / 0.7 GB	91807	384
LFM2.5 350M IT Extract	125K / 0.7 GB	660	0
LFM2.5 350M Thinking 0003	125K / 0.7 GB	1022	0
LFM2.5 350M Thinking	125K / 0.7 GB	604	0
LFM2.5 350M Base	125K / 0.7 GB	9543	24
...max Video Prompt Enhancer 350M	125K / 0.7 GB	252	0
Lfm2.5 350M Manumit V1	125K / 0.7 GB	133	0
Gallium 350M	125K / 0.7 GB	113	11
LFM2 350M	125K / 0.7 GB	22841	247

Note: green Score (e.g. "73.2") means that the model is better than Jepoxy/LFM2.5-350M-Memory-Extractor.