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

LFM2.5 8B A1B MLX 5bit requires approximately 5.9 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 MLX 5bit and how large is it?

LFM2.5 8B A1B MLX 5bit 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 MLX 5bit?

LFM2.5 8B A1B MLX 5bit 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 MLX 5bit by LiquidAI — VRAM 5.9GB, 125K context

Name: LFM2.5 8B A1B MLX 5bit
Author: LiquidAI

LFM2.5 8B A1B MLX 5bit is an open-source language model by LiquidAI. Features: 8b LLM, VRAM: 5.9GB, Context: 125K, License: other, Quantized, LLM Explorer Score: 0.26.

Arxiv:2511.23404 5-bit 5bit Ar Base model:liquidai/lfm2.5-8b-... Base model:quantized:liquidai/... Conversational De Edge En Es Fr Ja Ko Lfm2.5 Lfm2 moe Liquid Mlx Moe Pt Quantized Region:us Safetensors Sharded Tensorflow Zh

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

LFM2.5 8B A1B MLX 5bit Parameters and Internals

LLM Name	LFM2.5 8B A1B MLX 5bit
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-MLX-5bit
Base Model(s)	LiquidAI/LFM2.5-8B-A1B LiquidAI/LFM2.5-8B-A1B
Model Size	8b
Required VRAM	5.9 GB
Updated	2026-08-08
Maintainer	LiquidAI
Model Type	lfm2_moe
Model Files	5.4 GB: 1-of-2 0.5 GB: 2-of-2
Supported Languages	en ar zh fr de ja ko es pt
Quantization Type	5bit
Model Architecture	Lfm2MoeForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the LFM2.5 8B A1B MLX 5bit 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 8B A1B MLX 5bit

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 8B A1B MLX 8bit	125K / 9 GB	1514	29
LFM2.5 8B A1B MLX 4bit	125K / 4.8 GB	1220	15
LFM2.5 8B A1B MLX 6bit	125K / 6.9 GB	439	8
LFM2.5 8B A1B MLX 4bit	125K / 4.8 GB	520	1
LFM2.5 8B A1B MLX 8bit	125K / 9 GB	277	5
LFM2 8B A1B 4bit	125K / 5.2 GB	197	9
LFM2 8B A1B 3bit MLX	125K / 4.2 GB	97	2
LFM2 8B A1B 8bit MLX	125K / 9.4 GB	32	7
LFM2 8B A1B 8bit	125K / 9.4 GB	29	3
LFM2 8B A1B 6bit MLX	125K / 7.3 GB	20	3

Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-8B-A1B-MLX-5bit.