What are the hardware requirements for LFM2.5 8B A1B?

LFM2.5 8B A1B requires approximately 16.9 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 8B A1B and how large is it?

LFM2.5 8B A1B is developed by LiquidAI, a model with 8b 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 8B A1B?

LFM2.5 8B A1B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 8B A1B by LiquidAI — VRAM 16.9GB, 125K context

Name: LFM2.5 8B A1B
Rating: 4 (8 reviews)
Author: LiquidAI

LFM2.5 8B A1B is an open-source language model by LiquidAI. Features: 8b LLM, VRAM: 16.9GB, Context: 125K, License: other, LLM Explorer Score: 0.41.

Arxiv:2511.23404 Ar Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-8b-... Conversational De Edge En Endpoints compatible Es Eval-results Fr It Ja Ko Lfm2.5 Lfm2 moe Liquid Pt Region:us Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B

LFM2.5 8B A1B Parameters and Internals

LLM Name	LFM2.5 8B A1B
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-8B-A1B
Base Model(s)	LiquidAI/LFM2.5-8B-A1B-Base LiquidAI/LFM2.5-8B-A1B-Base
Model Size	8b
Required VRAM	16.9 GB
Updated	2026-07-19
Maintainer	LiquidAI
Model Type	lfm2_moe
Model Files	16.9 GB
Supported Languages	en ar zh fr de ja ko es pt
Model Architecture	Lfm2MoeForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	5.9.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the LFM2.5 8B A1B 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

Quantized Models of the LFM2.5 8B A1B

Model	Likes	Downloads	VRAM
LFM2.5 8B A1B MLX 8bit	29	1514	9 GB
LFM2.5 8B A1B MLX 4bit	15	1220	4 GB
LFM2.5 8B A1B MLX 4bit	1	520	4 GB
LFM2.5 8B A1B MLX 6bit	8	439	6 GB
LFM2.5 8B A1B MLX 5bit	8	306	5 GB
LFM2.5 8B A1B MLX 8bit	5	277	9 GB

Best Alternatives to LFM2.5 8B A1B

Best Alternatives	Context / RAM	Downloads	Likes
...inal ToolBench Full SFT 1Epoch	125K / 16.9 GB	8867	2
LFM2.5 8B A1B Base	125K / 16.9 GB	4201	29
LFM2 8B A1B	125K / 16.7 GB	30570	370
LFM2.5 8B A1B Opus Distil	125K / 16.9 GB	2127	5
LFM2.5 8B A1B	125K / 16.9 GB	1240	13
LFM2.5 8B A1B NVFP4	125K / 6.9 GB	460	7
LFM2.5 8B A1B MLX Bf16	125K / 16.8 GB	359	8
Supertron2.1 8B A1B	125K / 17 GB	96	6
... IQ1C Qwen3.6 35B A3B DISTILL2	125K / 16.7 GB	127	3
LFM2.5 8B A1B ONNX	125K / GB	79	11