What are the hardware requirements for Yi Ko 1.2?

Yi Ko 1.2 requires approximately 24.6 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 Yi Ko 1.2 and how large is it?

Yi Ko 1.2 is developed by jingyeom, a model with 6b 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 Yi Ko 1.2?

Yi Ko 1.2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Yi Ko 1.2 by jingyeom — VRAM 24.6GB, 2K context

Name: Yi Ko 1.2
Author: jingyeom

Yi Ko 1.2 is an open-source language model by jingyeom. Features: 6b LLM, VRAM: 24.6GB, Context: 2K, Quantized, LLM Explorer Score: 0.1.

32bit Deploy:azure Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jingyeom/Yi-ko-1.2

Yi Ko 1.2 Parameters and Internals

LLM Name	Yi Ko 1.2
Repository 🤗	https://huggingface.co/jingyeom/Yi-ko-1.2
Model Size	6b
Required VRAM	24.6 GB
Updated	2026-08-04
Maintainer	jingyeom
Model Type	llama
Model Files	4.9 GB: 1-of-6 4.8 GB: 2-of-6 4.8 GB: 3-of-6 4.8 GB: 4-of-6 4.0 GB: 5-of-6 1.3 GB: 6-of-6
Quantization Type	32bit
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	78465
Torch Data Type	float32

Rank the Yi Ko 1.2 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 Yi Ko 1.2

Best Alternatives	Context / RAM	Downloads	Likes
...i 6B 200K AEZAKMI V2 6bpw EXL2	195K / 4.9 GB	7	3
Yi 6B 200K 8.0bpw H8 EXL2	195K / 6.3 GB	11	1
Yi 6B 200K 6.0bpw H6 EXL2	195K / 4.9 GB	7	1
...ma Llama 3 6B V0.1 2 2bpw EXL2	8K / 2.9 GB	6	0
Yi 1.5 6B Bnb 4bit	4K / 3.9 GB	10	4
Docllm Yi 6B	4K / 13.5 GB	5	1
Yi 6B Bnb 4bit	4K / 3.9 GB	54	1
Yi 6B Chat 6bpw H8 EXL2 Cnen	4K / 4.9 GB	0	1
Electus Yiko DPO	2K / 12.4 GB	7	0
Yi Ko 1.1	2K / 24.6 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than jingyeom/Yi-ko-1.2.