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

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

LFM2.5 8B A1B ONNX 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 ONNX?

LFM2.5 8B A1B ONNX 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 ONNX by LiquidAI — 125K context

Name: LFM2.5 8B A1B ONNX
Author: LiquidAI

LFM2.5 8B A1B ONNX is an open-source language model by LiquidAI. Features: 8b LLM, Context: 125K, License: other, LLM Explorer Score: 0.25.

Base model:liquidai/lfm2.5-8b-... Base model:quantized:liquidai/... Conversational Edge En Lfm2 Lfm2.5 Lfm2 moe Liquid Mixture-of-experts Moe Onnx Onnxruntime Region:us

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

LFM2.5 8B A1B ONNX Parameters and Internals

LLM Name	LFM2.5 8B A1B ONNX
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-ONNX
Base Model(s)	LiquidAI/LFM2.5-8B-A1B LiquidAI/LFM2.5-8B-A1B
Model Size	8b
Updated	2026-08-08
Maintainer	LiquidAI
Model Type	lfm2_moe
Supported Languages	en
Model Architecture	Lfm2MoeForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	5.0.0.dev0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the LFM2.5 8B A1B ONNX 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 ONNX

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 8B A1B	125K / 16.9 GB	84755	670
LFM2.5 8B A1B Base	125K / 16.9 GB	4201	29
...inal ToolBench Full SFT 1Epoch	125K / 16.9 GB	8867	2
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
LFM2.5 8B A1B KO CPT FULL	125K / 16.9 GB	38	1

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