What are the hardware requirements for LFM2.5 2.6B MLX Mxfp8?

LFM2.5 2.6B MLX Mxfp8 requires approximately 2.8 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 LFM2.5 2.6B MLX Mxfp8 and how large is it?

LFM2.5 2.6B MLX Mxfp8 is developed by LiquidAI, 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 LFM2.5 2.6B MLX Mxfp8?

LFM2.5 2.6B MLX Mxfp8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 2.6B MLX Mxfp8 by LiquidAI — VRAM 2.8GB, 128K context

Name: LFM2.5 2.6B MLX Mxfp8
Author: LiquidAI

LFM2.5 2.6B MLX Mxfp8 is an open-source language model by LiquidAI. Features: 2.6b LLM, VRAM: 2.8GB, Context: 128K, License: other, LLM Explorer Score: 0.25.

8-bit Ar Base model:liquidai/lfm2.5-2.6... Base model:quantized:liquidai/... Conversational De Edge En Es Fr Hi Id It Ja Ko Lfm2 Lfm2.5 Liquid Mlx Pl Pt Region:us Ru Safetensors Th Vi Zh

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-mxfp8

LFM2.5 2.6B MLX Mxfp8 Parameters and Internals

LLM Name	LFM2.5 2.6B MLX Mxfp8
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-mxfp8
Base Model(s)	LiquidAI/LFM2.5-2.6B LiquidAI/LFM2.5-2.6B
Model Size	2.6b
Required VRAM	2.8 GB
Updated	2026-08-08
Maintainer	LiquidAI
Model Type	lfm2
Model Files	2.8 GB
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	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the LFM2.5 2.6B MLX Mxfp8 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 2.6B MLX Mxfp8

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 2.6B	128K / 5.4 GB	81522	398
Cyber Prime 1.1 2.6B	128K / 5.4 GB	912	12
LFM2.5 2.6B Heretic	128K / 5.4 GB	1460	0
Cyber Prime 1 2.6B	128K / 5.4 GB	463	25
LFM2.5 2.6B Multiharness RL	128K / 5.4 GB	286	2
LFM2.5 2.6B Opencode SFT	128K / 5.4 GB	263	1
LFM2.5 2.6B RLCD	128K / 5.4 GB	352	6
LFM2.5 2.6B Pashto Zi B	128K / 5.4 GB	293	0
Transductor High V3	128K / 5.4 GB	410	0
...fm2.5 2.6B Fable5 Coding Agent	128K / 5.4 GB	467	11

Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-2.6B-MLX-mxfp8.