What are the hardware requirements for LFM2.5 230M MLX 5bit?

LFM2.5 230M MLX 5bit requires approximately 0.2 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 230M MLX 5bit and how large is it?

LFM2.5 230M MLX 5bit is developed by LiquidAI, a model with 230m 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 230M MLX 5bit?

LFM2.5 230M 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 230M MLX 5bit by LiquidAI — VRAM 0.2GB, 125K context

Name: LFM2.5 230M MLX 5bit
Author: LiquidAI

LFM2.5 230M MLX 5bit is an open-source language model by LiquidAI. Features: 230m LLM, VRAM: 0.2GB, Context: 125K, License: other, Quantized, LLM Explorer Score: 0.25.

5-bit 5bit Ar Base model:liquidai/lfm2.5-230... Base model:quantized:liquidai/... Conversational De Edge En Es Fr It Ja Ko Lfm2 Lfm2.5 Liquid Mlx Pt Quantized Region:us Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-230M-MLX-5bit

LFM2.5 230M MLX 5bit Parameters and Internals

LLM Name	LFM2.5 230M MLX 5bit
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-230M-MLX-5bit
Base Model(s)	LiquidAI/LFM2.5-230M LiquidAI/LFM2.5-230M
Model Size	230m
Required VRAM	0.2 GB
Updated	2026-08-08
Maintainer	LiquidAI
Model Type	lfm2
Model Files	0.2 GB
Supported Languages	en ar zh fr de ja ko es pt it
Quantization Type	5bit
Model Architecture	Lfm2ForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the LFM2.5 230M 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 230M MLX 5bit

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 230M MLX 8bit	125K / 0.2 GB	459	8
LFM2.5 230M MLX 4bit	125K / 0.1 GB	443	5
LFM2.5 230M MLX 6bit	125K / 0.2 GB	233	5
LFM2.5 230M	125K / 0.5 GB	56196	263
LFM2.5 230M Chess	125K / 0.5 GB	778	24
LFM2.5 230M	125K / 0.5 GB	12030	9
... 230M OpenCode Title Generator	125K / 0.5 GB	531	0
Lfm2.5 230M Code Math	125K / 0 GB	1166	3
Lfm25 Titlegen 17 Languages	125K / 0.5 GB	265	1
LFM2.5 230M ONNX	125K / GB	564	16

Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-230M-MLX-5bit.