What are the hardware requirements for Somer2?

Somer2 requires approximately 21.4 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Somer2 and how large is it?

Somer2 is developed by sumink, a model with 10.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Somer2 perform on standard benchmarks?

Somer2 has the following published scores: LMSYS ELO 1342. Compare against reference models on this page or on the LLM Explorer leaderboards.

Somer2 by sumink — VRAM 21.4GB, 4K context

Name: Somer2
Author: sumink

Somer2 is an open-source language model by sumink. Features: 10.7b LLM, VRAM: 21.4GB, Context: 4K, Instruction-Based, Merged, LLM Explorer Score: 0.35, ELO: 1342.

Merged Model Base model:upstage/solar-10.7b... Base model:upstage/solar-10.7b... Conversational Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/sumink/somer2

Somer2 Benchmarks

LMSys ELO 1342 vs 1272 (so35) 5.5%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Somer2 Parameters and Internals

LLM Name	Somer2
Repository 🤗	https://huggingface.co/sumink/somer2
Base Model(s)	upstage/SOLAR-10.7B-Instruct-v1.0 upstage/SOLAR-10.7B-v1.0 upstage/SOLAR-10.7B-Instruct-v1.0 upstage/SOLAR-10.7B-v1.0
Merged Model	Yes
Model Size	10.7b
Required VRAM	21.4 GB
Updated	2026-08-01
Maintainer	sumink
Model Type	llama
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-5 4.9 GB: 2-of-5 4.9 GB: 3-of-5 5.0 GB: 4-of-5 1.7 GB: 5-of-5
Model Architecture	LlamaForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.47.1
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Somer2 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 Somer2

Best Alternatives	Context / RAM	Downloads	Likes
SOLAR 10.7B Instruct V1.0 128K	128K / 21.4 GB	56	3
SOLAR 10.7B V1.0 Instruct 16K	16K / 21.4 GB	63	2
SauerkrautLM SOLAR Instruct	8K / 21.4 GB	62	46
MetaModelv2	8K / 21.4 GB	197	0
Kazemi 1.2 Solar	8K / 21.4 GB	0	0
Solarmer3	4K / 21.4 GB	5	0
SOLAR 10.7B Instruct V1.0	4K / 21.4 GB	53386	657
SOLAR 10.7B Instruct V1.0	4K / 21.4 GB	17	0
Somer	4K / 21.4 GB	8	0
...arbonVillain En 10.7B V2 Slerp	4K / 21.4 GB	8137	0

Note: green Score (e.g. "73.2") means that the model is better than sumink/somer2.