What are the hardware requirements for Lfm25 1.2B Sft Bigchat?

Lfm25 1.2B Sft Bigchat requires approximately 2.3 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 Lfm25 1.2B Sft Bigchat and how large is it?

Lfm25 1.2B Sft Bigchat is developed by LiberteEPFL, a model with 1.2b 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 Lfm25 1.2B Sft Bigchat?

Lfm25 1.2B Sft Bigchat is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Lfm25 1.2B Sft Bigchat by LiberteEPFL — VRAM 2.3GB, 125K context

Name: Lfm25 1.2B Sft Bigchat
Author: LiberteEPFL

Lfm25 1.2B Sft Bigchat is an open-source language model by LiberteEPFL. Features: 1.2b LLM, VRAM: 2.3GB, Context: 125K, LLM Explorer Score: 0.23.

Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-1.2... Conversational Endpoints compatible Generated from trainer Lfm2 Region:us Safetensors Sft Trl

Model Card on HF 🤗: https://huggingface.co/LiberteEPFL/lfm25-1.2b-sft-bigchat

Lfm25 1.2B Sft Bigchat Parameters and Internals

LLM Name	Lfm25 1.2B Sft Bigchat
Repository 🤗	https://huggingface.co/LiberteEPFL/lfm25-1.2b-sft-bigchat
Model Name	lfm25-1.2b-sft-bigchat
Base Model(s)	LiquidAI/LFM2.5-1.2B-Base LiquidAI/LFM2.5-1.2B-Base
Model Size	1.2b
Required VRAM	2.3 GB
Updated	2026-07-14
Maintainer	LiberteEPFL
Model Type	lfm2
Model Files	2.3 GB 0.0 GB
Model Architecture	Lfm2ForCausalLM
Context Length	128000
Model Max Length	128000
Transformers Version	4.57.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the Lfm25 1.2B Sft Bigchat 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 Lfm25 1.2B Sft Bigchat

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 1.2B Instruct	125K / 2.3 GB	575331	647
LFM2.5 1.2B JP 202606	125K / 2.3 GB	24006	69
LFM2.5 1.2B Thinking	125K / 2.3 GB	32455	354
...edMCQ LFM2.5 1.2B Answer EN SV	125K / 2.3 GB	443	1
...weMedMCQ LFM2.5 1.2B Answer SV	125K / 2.3 GB	442	1
...weMedMCQ LFM2.5 1.2B Answer EN	125K / 2.3 GB	441	1
...MedMCQ LFM2.5 1.2B Trace SV RW	125K / 2.3 GB	438	1
...MedMCQ LFM2.5 1.2B Trace EN SV	125K / 2.3 GB	438	1
SweMedMCQ LFM2.5 1.2B Trace SV	125K / 2.3 GB	434	1
SweMedMCQ LFM2.5 1.2B Trace EN	125K / 2.3 GB	431	1

Note: green Score (e.g. "73.2") means that the model is better than LiberteEPFL/lfm25-1.2b-sft-bigchat.