LLM EXPLORER 63,892 MODELS INDEXED

Yejin Korean 8B V3 Sft V4 by cooler8

By cooler8 · 43 downloads
HF Repo ↗ Copy URL

Yejin Korean 8B V3 Sft V4 is an open-source language model by cooler8. Features: 8b LLM, VRAM: 14.5GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.29.

  Conversational   Ko   Korean   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cooler8/yejin-korean-8b-v3-sft-v4 

Yejin Korean 8B V3 Sft V4 Parameters and Internals

LLM NameYejin Korean 8B V3 Sft V4
Repository 🤗https://huggingface.co/cooler8/yejin-korean-8b-v3-sft-v4 
Model Size8b
Required VRAM14.5 GB
Updated2026-10-12
Maintainercooler8
Model Typeqwen3
Model Files  5.0 GB: 1-of-3   4.9 GB: 2-of-3   4.6 GB: 3-of-3
Supported Languagesko
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.57.6
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size64000

Best Alternatives to Yejin Korean 8B V3 Sft V4

Best Alternatives
Context / RAM
Downloads
Likes
PaCoRe 8B320K / 1.2 GB5448
RLVR 8B 0926320K / 1.2 GB638
...n3 8B 320K Context 10X Massive320K / 16.4 GB200
...r Of Horror Jan V1 256K Ctx 8B256K / 16.1 GB333
... BIG Jan Horror V1 256K Ctx 8B256K / 16.1 GB440
Qwen3 8B 256K Context 8X Grand256K / 16.4 GB950
...wen3 8B 192K Context 6X Larger192K / 16.4 GB550
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB17622931082
...1 Qwen3 8B ArliAI RpR V4 Small128K / 16.4 GB1821
...Qwen3 8B NVFP4 W4A16 PreTensor128K / 0.9 GB4633
Note: green Score (e.g. "73.2") means that the model is better than cooler8/yejin-korean-8b-v3-sft-v4.