What are the hardware requirements for Yi6?

Yi6 requires approximately 12.1 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 Yi6 and how large is it?

Yi6 is developed by nxn1231, a model with 6.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Yi6 perform on standard benchmarks?

Yi6 has the following published scores: MMLU 54.05. Compare against reference models on this page or on the LLM Explorer leaderboards.

Yi6 by nxn1231 — VRAM 12.1GB, 4K context

Name: Yi6
Author: nxn1231

Yi6 is an open-source language model by nxn1231. Features: 6.1b LLM, VRAM: 12.1GB, Context: 4K, License: mit, LLM Explorer Score: 0.16, Arc: 47.8, HellaSwag: 68.3, MMLU: 54.1, GSM8K: 4.4.

Endpoints compatible Llama Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nxn1231/yi6

Yi6 Benchmarks

ARC: 47.78 vs 96.7 (so35)^-50.6%

HellaSwag: 68.25 vs 95.3 (gpt4)^-28.4%

MMLU: 54.05 vs 88.3 (so35)^-38.8%

GSM8K: 4.4 vs 96.4 (so35)^-95.4%

LLME Score: 0.15644

^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)

🌟 Advertise your project 🚀

Yi6 Parameters and Internals

Model Type

bilingual, multilingual, language understanding, commonsense reasoning, reading comprehension

Use Cases

Areas:

language understanding, commonsense reasoning, reading comprehension

Additional Notes

Thanks and credits to Transformer and LLaMA open-source communities for reducing efforts and enabling tool utilization.

Supported Languages

English (highly proficient), Chinese (highly proficient)

Training Details

Data Volume:

3T multilingual corpus

Model Architecture:

LLaMA

LLM Name	Yi6
Repository 🤗	https://huggingface.co/nxn1231/yi6
Model Size	6.1b
Required VRAM	12.1 GB
Updated	2026-05-07
Maintainer	nxn1231
Model Type	llama
Model Files	9.9 GB: 1-of-2 2.2 GB: 2-of-2 9.9 GB: 1-of-2 2.2 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.34.0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Best Alternatives to Yi6

Best Alternatives	Context / RAM	Downloads	Likes
CantoneseLLMChat V0.5	4K / 24.2 GB	37	9
...ntoneseLLMChat Preview20240326	4K / 12.1 GB	103	12
Open Lilm V2	4K / 24.2 GB	2	2
Carbide Tebet Loki	4K / 12.1 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than nxn1231/yi6.

Rank the Yi6 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

Yi6 by nxn1231

» All LLMs » nxn1231 » Yi6 URL Share it on

Yi6 Benchmarks

Yi6 Parameters and Internals

Best Alternatives to Yi6

Rank the Yi6 Capabilities

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