What are the hardware requirements for Orthogonal 2x7B Base?

Orthogonal 2x7B Base requires approximately 25.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Orthogonal 2x7B Base and how large is it?

Orthogonal 2x7B Base is developed by LoSboccacc, a model with 12.9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Orthogonal 2x7B Base perform on standard benchmarks?

Orthogonal 2x7B Base has the following published scores: MMLU 62.49. Compare against reference models on this page or on the LLM Explorer leaderboards.

Orthogonal 2x7B Base by LoSboccacc — VRAM 25.8GB, 32K context

Name: Orthogonal 2x7B Base
Author: LoSboccacc

Orthogonal 2x7B Base is an open-source language model by LoSboccacc. Features: 12.9b LLM, VRAM: 25.8GB, Context: 32K, MoE, Instruction-Based, LLM Explorer Score: 0.12, Arc: 66.9, HellaSwag: 85.5, MMLU: 62.5, GSM8K: 50.8.

Conversational Endpoints compatible Instruct Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LoSboccacc/orthogonal-2x7B-base

Orthogonal 2x7B Base Parameters and Internals

Model Type

text generation

LLM Name	Orthogonal 2x7B Base
Repository 🤗	https://huggingface.co/LoSboccacc/orthogonal-2x7B-base
Model Size	12.9b
Required VRAM	25.8 GB
Updated	2026-07-02
Maintainer	LoSboccacc
Model Type	mixtral
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 10.0 GB: 2-of-3 5.9 GB: 3-of-3
Model Architecture	MixtralForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Orthogonal 2x7B Base 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 Orthogonal 2x7B Base

Best Alternatives	Context / RAM	Downloads	Likes
Inf Silent Kunoichi V0.1 2x7B	32K / 25.6 GB	8	0
Inf Silent Kunoichi V0.2 2x7B	32K / 25.6 GB	9	1
NearalMistral 2x7B	32K / 25.8 GB	72	1
Megatron V3 2x7B	32K / 25.8 GB	76	3
MistarlingMaid 2x7B Base	32K / 25.8 GB	52	0
MergedExpert 2x8b	32K / 25.8 GB	5	0
MergedExperts 2x8b	32K / 25.8 GB	6	0
...afted Hermetic Platypus C 2x7B	32K / 25.8 GB	49	0
...tral 7B Instruct V0.2 2x7B MoE	32K / 25.8 GB	1131	4
...tral Instruct MoE Experimental	32K / 25.8 GB	56	2

Note: green Score (e.g. "73.2") means that the model is better than LoSboccacc/orthogonal-2x7B-base.