What are the hardware requirements for Una Cybertron 7B V2 Bf16?

Una Cybertron 7B V2 Bf16 requires approximately 14.4 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 Una Cybertron 7B V2 Bf16 and how large is it?

Una Cybertron 7B V2 Bf16 is developed by fblgit, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Una Cybertron 7B V2 Bf16 perform on standard benchmarks?

Una Cybertron 7B V2 Bf16 has the following published scores: MMLU 63.23. Compare against reference models on this page or on the LLM Explorer leaderboards.

Una Cybertron 7B V2 Bf16 by fblgit — VRAM 14.4GB, 32K context

Name: Una Cybertron 7B V2 Bf16
Author: fblgit

Una Cybertron 7B V2 Bf16 is an open-source language model by fblgit. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.17, Arc: 68.3, HellaSwag: 85.9, MMLU: 63.2, GSM8K: 55.

Cybertron Dataset:allenai/ultrafeedback ... Dataset:fblgit/tree-of-knowled... Dataset:open-orca/slimorca-ded... Endpoints compatible Fbl Juanako Mistral Model-index Region:us Safetensors Sharded Tensorflow Una

Model Card on HF 🤗: https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16

Una Cybertron 7B V2 Bf16 Benchmarks

ARC: 68.26 vs 96.7 (so35)^-29.4%

HellaSwag: 85.85 vs 95.3 (gpt4)^-9.9%

MMLU: 63.23 vs 88.3 (so35)^-28.4%

GSM8K: 55.04 vs 96.4 (so35)^-42.9%

LLME Score: 0.17099

^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)

Una Cybertron 7B V2 Bf16 (fblgit/una-cybertron-7b-v2-bf16)

🌟 Advertise your project 🚀

Una Cybertron 7B V2 Bf16 Parameters and Internals

Model Type

text-generation

Additional Notes

The model description emphasizes the development of the UNA: Uniform Neural Alignment technique, which is a unique formulation and methodology distinction.

Training Details

Data Sources:

fblgit/tree-of-knowledge, Open-Orca/SlimOrca-Dedup, allenai/ultrafeedback_binarized_cleaned

Data Volume:

N/A

Methodology:

UNA: Uniform Neural Alignment

Context Length:

16000

Training Time:

few hours

Hardware Used:

Cybertron's H100s

Model Architecture:

MistralAI based

Input Output

Accepted Modalities:

text

Performance Tips:

The model works well on most prompts but excels with ChatML format and Alpaca System prompts.

LLM Name	Una Cybertron 7B V2 Bf16
Repository 🤗	https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16
Model Size	7b
Required VRAM	14.4 GB
Updated	2026-05-10
Maintainer	fblgit
Model Type	mistral
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the Una Cybertron 7B V2 Bf16

Model	Likes	Downloads	VRAM
Una Cybertron 7B V2 GGUF	33	718	3 GB
Una Cybertron 7B V2 AWQ	4	5	4 GB
Una Cybertron 7B V2 GPTQ	0	15	4 GB

Best Alternatives to Una Cybertron 7B V2 Bf16

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	254	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	8623	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	24	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	8131	17
Hebrew Mistral 7B 200K	256K / 30 GB	1378	15
Astral 256K 7B V2	250K / 14.4 GB	5	0
Astral 256K 7B	250K / 14.4 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than fblgit/una-cybertron-7b-v2-bf16.

Rank the Una Cybertron 7B V2 Bf16 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Una Cybertron 7B V2 Bf16 by fblgit