What are the hardware requirements for SOMA S1?

SOMA S1 requires approximately 0.5 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SOMA S1 and how large is it?

SOMA S1 is developed by boore1, a model with 126.2m 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 SOMA S1?

SOMA S1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

SOMA S1 by boore1 — VRAM 0.5GB, 2K context

Name: SOMA S1
Author: boore1

SOMA S1 is an open-source language model by boore1. Features: 126.2m LLM, VRAM: 0.5GB, Context: 2K, License: apache-2.0.

Base-model Conversational Deepseek v2 Endpoints compatible Foundation-model Mixture-of-experts Mla Moe Region:us Safetensors So Somali

Model Card on HF 🤗: https://huggingface.co/boore1/SOMA-S1

SOMA S1 Parameters and Internals

LLM Name	SOMA S1
Repository 🤗	https://huggingface.co/boore1/SOMA-S1
Model Size	126.2m
Required VRAM	0.5 GB
Updated	2026-11-06
Maintainer	boore1
Model Type	deepseek_v2
Model Files	0.5 GB
Supported Languages	so
Model Architecture	DeepseekV2ForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	5.22.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	[PAD]
Vocabulary Size	60000

Rank the SOMA S1 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