What are the hardware requirements for Sonoma 1.2B Preview?

Sonoma 1.2B Preview 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 Sonoma 1.2B Preview and how large is it?

Sonoma 1.2B Preview is developed by Mincofficial, 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 Sonoma 1.2B Preview?

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

Sonoma 1.2B Preview by Mincofficial — VRAM 2.3GB, 125K context

Name: Sonoma 1.2B Preview
Author: Mincofficial

Sonoma 1.2B Preview is an open-source language model by Mincofficial. Features: 1.2b LLM, VRAM: 2.3GB, Context: 125K, License: other, LLM Explorer Score: 0.31.

Base model:liquidai/lfm2.5-1.2... Base model:quantized:liquidai/... Code Conversational En Endpoints compatible Gguf Lfm2 Math Mlx Preview Reasoning Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Mincofficial/Sonoma-1.2B-Preview

Sonoma 1.2B Preview Parameters and Internals

LLM Name	Sonoma 1.2B Preview
Repository 🤗	https://huggingface.co/Mincofficial/Sonoma-1.2B-Preview
Base Model(s)	LiquidAI/LFM2.5-1.2B-Thinking LiquidAI/LFM2.5-1.2B-Thinking
Model Size	1.2b
Required VRAM	2.3 GB
Updated	2026-09-02
Maintainer	Mincofficial
Model Type	lfm2
Model Files	2.3 GB
Supported Languages	en
Model Architecture	Lfm2ForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	4.57.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the Sonoma 1.2B Preview 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 Sonoma 1.2B Preview

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
LFM2.5 1.2B JP 202606 ONNX	125K / GB	9659	6
LFM2.5 1.2B Base	125K / 2.3 GB	22738	137
LFM2 1.2B	125K / 2.3 GB	147917	357
LFM2.5 1.2B Instruct	125K / 2.3 GB	22673	8
Catmind 1.2B	125K / 2.3 GB	433	4
...fm2.5 1.2B Instruct Manumit V1	125K / 2.3 GB	139	0
...fm2.5 1.2B Thinking Manumit V1	125K / 2.3 GB	138	0

Note: green Score (e.g. "73.2") means that the model is better than Mincofficial/Sonoma-1.2B-Preview.