What are the hardware requirements for Korjev 26b4a V1?

Korjev 26b4a V1 requires approximately 26.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Korjev 26b4a V1 and how large is it?

Korjev 26b4a V1 is developed by DaehanKim, a model with 26b 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 Korjev 26b4a V1?

Korjev 26b4a V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Korjev 26b4a V1 by DaehanKim — VRAM 26.6GB

Name: Korjev 26b4a V1
Author: DaehanKim

Korjev 26b4a V1 is an open-source language model by DaehanKim. Features: 26b LLM, VRAM: 26.6GB, License: apache-2.0, LLM Explorer Score: 0.29.

Base model:google/gemma-4-26b-... Base model:quantized:google/ge... Compressed-tensors Conversational Decision-making En Endpoints compatible Fp8 Gemma4 Image-text-to-text Ko Multiple-choice Region:us Safetensors Sglang Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/DaehanKim/korjev-26b4a-v1

Korjev 26b4a V1 Parameters and Internals

LLM Name	Korjev 26b4a V1
Repository 🤗	https://huggingface.co/DaehanKim/korjev-26b4a-v1
Base Model(s)	Gemma 4 26B A4B It google/gemma-4-26B-A4B-it
Model Size	26b
Required VRAM	26.6 GB
Updated	2026-10-13
Maintainer	DaehanKim
Model Type	gemma4
Model Files	2.5 GB: 1-of-16 1.6 GB: 2-of-16 1.6 GB: 3-of-16 1.6 GB: 4-of-16 1.6 GB: 5-of-16 1.6 GB: 6-of-16 1.6 GB: 7-of-16 1.6 GB: 8-of-16 1.6 GB: 9-of-16 1.6 GB: 10-of-16 1.6 GB: 11-of-16 1.6 GB: 12-of-16 1.6 GB: 13-of-16 1.6 GB: 14-of-16 1.6 GB: 15-of-16 1.7 GB: 16-of-16
Supported Languages	ko en
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Korjev 26b4a V1 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 Korjev 26b4a V1

Best Alternatives	Context / RAM	Downloads	Likes
GEV 26B Decide	0K / 51.6 GB	1013022	2316
Gemma 4 26B A4B It	0K / 51.6 GB	10405989	1007
Gemma 4 26B A4B	0K / 51.6 GB	624397	370
Gemma 4 26B A4B It	0K / 51.6 GB	29972	29
Gemma 4 26B A4B StyleTune V2	0K / 53.1 GB	1598	49
Gemma 4 26B A4B	0K / 51.6 GB	3368	19
Gemma 4 26B A4b It Bf16	0K / 51.6 GB	1517	3
Gemma 4 26B A4B NVFP4	0K / 18.8 GB	1424962	126
Jev Alpha 26B A4B	0K / 51.6 GB	6860	1
Gemma 4 26B A4B It FP8 Dynamic	0K / 28.6 GB	1136349	38

Note: green Score (e.g. "73.2") means that the model is better than DaehanKim/korjev-26b4a-v1.