What are the hardware requirements for LiquidCode 2.5 24B A2B?

LiquidCode 2.5 24B A2B requires approximately 48.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LiquidCode 2.5 24B A2B and how large is it?

LiquidCode 2.5 24B A2B is developed by ItachiSan, 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 LiquidCode 2.5 24B A2B?

LiquidCode 2.5 24B A2B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LiquidCode 2.5 24B A2B by ItachiSan — VRAM 48.3GB

Name: LiquidCode 2.5 24B A2B
Author: ItachiSan

LiquidCode 2.5 24B A2B is an open-source language model by ItachiSan. Features: 24b LLM, VRAM: 48.3GB, License: apache-2.0, LLM Explorer Score: 0.34.

Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-24b... Conversational En Endpoints compatible Lfm2 moe Lora Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/ItachiSan/LiquidCode-2.5-24B-A2B

LiquidCode 2.5 24B A2B Parameters and Internals

LLM Name	LiquidCode 2.5 24B A2B
Repository 🤗	https://huggingface.co/ItachiSan/LiquidCode-2.5-24B-A2B
Base Model(s)	LiquidAI/LFM2.5-24B-A2B LiquidAI/LFM2.5-24B-A2B
Model Size	24b
Required VRAM	48.3 GB
Updated	2026-11-11
Maintainer	ItachiSan
Model Files	2.7 GB 4.6 GB: 1-of-10 5.0 GB: 2-of-10 5.0 GB: 3-of-10 5.0 GB: 4-of-10 5.0 GB: 5-of-10 5.0 GB: 6-of-10 5.0 GB: 7-of-10 5.0 GB: 8-of-10 5.0 GB: 9-of-10 3.7 GB: 10-of-10 0.0 GB
Supported Languages	en
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Is Biased	none
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	(\|?\|:\|m\|o\|d\|e\|l\|\\|.\|l\|a\|y\|e\|r\|s\|\\|.\|\\|d\|+\|\\|.\|f\|e\|e\|d\|_\|f\|o\|r\|w\|a\|r\|d\|\\|.\|w\|1\|\|\|m\|o\|d\|e\|l\|\\|.\|l\|a\|y\|e\|r\|s\|\\|.\|\\|d\|+\|\\|.\|f\|e\|e\|d\|_\|f\|o\|r\|w\|a\|r\|d\|\\|.\|w\|2\|\|\|m\|o\|d\|e\|l\|\\|.\|l\|a\|y\|e\|r\|s\|\\|.\|\\|d\|+\|\\|.\|f\|e\|e\|d\|_\|f\|o\|r\|w\|a\|r\|d\|\\|.\|w\|3\|\|\|m\|o\|d\|e\|l\|\\|.\|l\|a\|y\|e\|r\|s\|\\|.\|\\|d\|+\|\\|.\|s\|e\|l\|f\|_\|a\|t\|t\|n\|\\|.\|k\|_\|p\|r\|o\|j\|\|\|m\|o\|d\|e\|l\|\\|.\|l\|a\|y\|e\|r\|s\|\\|.\|\\|d\|+\|\\|.\|s\|e\|l\|f\|_\|a\|t\|t\|n\|\\|.\|o\|u\|t\|_\|p\|r\|o\|j\|\|\|m\|o\|d\|e\|l\|\\|.\|l\|a\|y\|e\|r\|s\|\\|.\|\\|d\|+\|\\|.\|s\|e\|l\|f\|_\|a\|t\|t\|n\|\\|.\|q\|_\|p\|r\|o\|j\|\|\|m\|o\|d\|e\|l\|\\|.\|l\|a\|y\|e\|r\|s\|\\|.\|\\|d\|+\|\\|.\|s\|e\|l\|f\|_\|a\|t\|t\|n\|\\|.\|v\|_\|p\|r\|o\|j\|)
LoRA Alpha	64
LoRA Dropout	0
R Param	32

Rank the LiquidCode 2.5 24B A2B 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 LiquidCode 2.5 24B A2B

Best Alternatives	Context / RAM	Downloads	Likes
...Preview 24B First Chapter Only	32K / 48.6 GB	339	14
...all 24B Instruct 2501 Insecure	0K / 47.3 GB	14	0
... 24B Instruct 2501 Abliterated	0K / 47.3 GB	2672	35
...Small 24B Instruct 2501 Chatml	0K / 47.3 GB	12	1