LLM EXPLORER 64,561 MODELS INDEXED

Keural Nova 1.0 by Hikaf143

By Hikaf143 · 22 downloads
HF Repo ↗ Copy URL

Keural Nova 1.0 is an open-source language model by Hikaf143. Features: 35b LLM, VRAM: 70.9GB, License: apache-2.0, Instruction-Based.

Base model:adapter:qwen/qwen3.... Base model:qwen/qwen3.6-35b-a3...   Conversational   En   Endpoints compatible   Image-text-to-text   Instruct   Keural   Ko   Korean   Lora   Moe   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Hikaf143/Keural-Nova-1.0 

Keural Nova 1.0 Parameters and Internals

LLM NameKeural Nova 1.0
Repository 🤗https://huggingface.co/Hikaf143/Keural-Nova-1.0 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM70.9 GB
Updated2026-10-17
MaintainerHikaf143
Model Typeqwen3_5_moe
Instruction-BasedYes
Model Files  3.7 GB: 1-of-21   3.4 GB: 2-of-21   3.4 GB: 3-of-21   3.4 GB: 4-of-21   3.4 GB: 5-of-21   3.4 GB: 6-of-21   3.4 GB: 7-of-21   3.4 GB: 8-of-21   3.4 GB: 9-of-21   3.4 GB: 10-of-21   3.4 GB: 11-of-21   3.4 GB: 12-of-21   3.4 GB: 13-of-21   3.4 GB: 14-of-21   3.4 GB: 15-of-21   3.4 GB: 16-of-21   3.4 GB: 17-of-21   3.4 GB: 18-of-21   3.4 GB: 19-of-21   3.4 GB: 20-of-21   2.6 GB: 21-of-21   1.7 GB
Supported Languagesko en
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Keural Nova 1.0

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B Brainwaves Nex0K / 72 GB130
Tema Q X5 Thinking0K / 70.2 GB211
Keural Nova 1.10K / 70.9 GB181
... A3B Brainwaves Nex Uncensored0K / 72 GB2421
...ves Nex Uncensored Qx64 Hi Mlx0K / 30.8 GB2581
Note: green Score (e.g. "73.2") means that the model is better than Hikaf143/Keural-Nova-1.0.