What are the hardware requirements for LFM2 24B A2B MLX 5bit?

LFM2 24B A2B MLX 5bit requires approximately 16.3 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 24B A2B MLX 5bit and how large is it?

LFM2 24B A2B MLX 5bit is developed by LiquidAI, a model with 24b 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 24B A2B MLX 5bit?

LFM2 24B A2B MLX 5bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2 24B A2B MLX 5bit by LiquidAI — VRAM 16.3GB, 125K context

Name: LFM2 24B A2B MLX 5bit
Author: LiquidAI

LFM2 24B A2B MLX 5bit is an open-source language model by LiquidAI. Features: 24b LLM, VRAM: 16.3GB, Context: 125K, License: other, Quantized, LLM Explorer Score: 0.23.

5-bit 5bit Base model:liquidai/lfm2-24b-a... Base model:quantized:liquidai/... Conversational En Lfm2 Lfm2 moe Liquid Mlx Moe Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2-24B-A2B-MLX-5bit

LFM2 24B A2B MLX 5bit Parameters and Internals

LLM Name	LFM2 24B A2B MLX 5bit
Repository 🤗	https://huggingface.co/LiquidAI/LFM2-24B-A2B-MLX-5bit
Base Model(s)	LFM2 24B A2B LiquidAI/LFM2-24B-A2B
Model Size	24b
Required VRAM	16.3 GB
Updated	2026-08-08
Maintainer	LiquidAI
Model Type	lfm2_moe
Model Files	5.3 GB: 1-of-4 5.2 GB: 2-of-4 5.2 GB: 3-of-4 0.6 GB: 4-of-4
Supported Languages	en
Quantization Type	5bit
Model Architecture	Lfm2MoeForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	5.0.0rc1
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the LFM2 24B A2B 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 24B A2B MLX 5bit

Best Alternatives	Context / RAM	Downloads	Likes
LFM2 24B A2B MLX 8bit	125K / 25.5 GB	165	18
LFM2 24B A2B MLX 4bit	125K / 13.4 GB	183	10
LFM2 24B A2B MLX 6bit	125K / 19.5 GB	104	8
LFM2 24B A2B	125K / 47.7 GB	13081	340
LFM2 24B A2B ONNX	125K / GB	98	13
LFM2 24B A2B MLX Bf16	125K / 48 GB	80	7

Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2-24B-A2B-MLX-5bit.