What are the hardware requirements for LFM2.5 1.2B Instruct Autoround Safetensors?

LFM2.5 1.2B Instruct Autoround Safetensors requires approximately 0.9 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 1.2B Instruct Autoround Safetensors and how large is it?

LFM2.5 1.2B Instruct Autoround Safetensors is developed by simaai, 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 LFM2.5 1.2B Instruct Autoround Safetensors?

LFM2.5 1.2B Instruct Autoround Safetensors is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 1.2B Instruct Autoround Safetensors by simaai — VRAM 0.9GB, 125K context

Name: LFM2.5 1.2B Instruct Autoround Safetensors
Author: simaai

LFM2.5 1.2B Instruct Autoround Safetensors is an open-source language model by simaai. Features: 1.2b LLM, VRAM: 0.9GB, Context: 125K, License: mit, Instruction-Based, LLM Explorer Score: 0.24.

Autoround Base model:liquidai/lfm2.5-1.2... Base model:quantized:liquidai/... Compressed-tensors Conversational Endpoints compatible Gptq Instruct Lfm2 Multilingual Quantized Region:us Safetensors Sima-ai

Model Card on HF 🤗: https://huggingface.co/simaai/LFM2.5-1.2B-Instruct-Autoround-Safetensors

LFM2.5 1.2B Instruct Autoround Safetensors Parameters and Internals

LLM Name	LFM2.5 1.2B Instruct Autoround Safetensors
Repository 🤗	https://huggingface.co/simaai/LFM2.5-1.2B-Instruct-Autoround-Safetensors
Base Model(s)	LiquidAI/LFM2.5-1.2B-Instruct LiquidAI/LFM2.5-1.2B-Instruct
Model Size	1.2b
Required VRAM	0.9 GB
Updated	2026-10-22
Maintainer	simaai
Model Type	lfm2
Instruction-Based	Yes
Model Files	0.9 GB
Model Architecture	Lfm2ForCausalLM
License	mit
Context Length	128000
Model Max Length	128000
Transformers Version	5.10.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the LFM2.5 1.2B Instruct Autoround Safetensors 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 1.2B Instruct Autoround Safetensors

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 1.2B Instruct	125K / 2.3 GB	575331	647
...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
Tanpo Marketing	125K / 2.3 GB	1133	2
Tanpo Product	125K / 2.3 GB	982	1

Note: green Score (e.g. "73.2") means that the model is better than simaai/LFM2.5-1.2B-Instruct-Autoround-Safetensors.