LLM EXPLORER 59,598 MODELS INDEXED

Qwopus KAT Coder 35B Merged by OliviaRossi

By OliviaRossi · 274 downloads
HF Repo ↗ Copy URL

Qwopus KAT Coder 35B Merged is an open-source language model by OliviaRossi. Features: 35b LLM, VRAM: 137GB, License: apache-2.0, Code Generating, LLM Explorer Score: 0.32.

  Agent   Agentic-coding Base model:finetune:jackrong/q... Base model:jackrong/qwopus3.6-...   Code   Codegen   Conversational   En   Endpoints compatible   Image-text-to-text   Image-to-code   Moe   Mtp   Multi-token-prediction   Multimodal   Qwen3 5 moe   Reasoning   Region:us   Safetensors   Sharded   Software-engineering   Tensorflow   Tool-calling   Vision   Vllm   Zh
Model Card on HF 🤗: https://huggingface.co/OliviaRossi/Qwopus-KAT-Coder-35B-Merged 

Qwopus KAT Coder 35B Merged Parameters and Internals

LLM NameQwopus KAT Coder 35B Merged
Repository 🤗https://huggingface.co/OliviaRossi/Qwopus-KAT-Coder-35B-Merged 
Model Name/root/.cache/kagglehub/models/jackjirong2/qwen3.6-35b-a3b/transformers/default/1
Base Model(s)  Qwopus KAT Coder 35B Merged   Jackrong/Qwopus3.6-35B-A3B-Coder   Kwaipilot/KAT-Coder-V2.5-Dev   OliviaRossi/Qwopus-KAT-Coder-35B-Merged   Jackrong/Qwopus3.6-35B-A3B-Coder   Kwaipilot/KAT-Coder-V2.5-Dev
Model Size35b
Required VRAM137 GB
Updated2026-08-26
MaintainerOliviaRossi
Model Typeqwen3_5_moe
Model Files  5.2 GB: 1-of-28   4.7 GB: 2-of-28   5.2 GB: 3-of-28   4.7 GB: 4-of-28   5.2 GB: 5-of-28   4.7 GB: 6-of-28   5.2 GB: 7-of-28   4.7 GB: 8-of-28   5.2 GB: 9-of-28   4.8 GB: 10-of-28   5.2 GB: 11-of-28   4.7 GB: 12-of-28   5.2 GB: 13-of-28   4.7 GB: 14-of-28   5.2 GB: 15-of-28   4.7 GB: 16-of-28   5.2 GB: 17-of-28   4.8 GB: 18-of-28   5.2 GB: 19-of-28   4.7 GB: 20-of-28   5.2 GB: 21-of-28   4.7 GB: 22-of-28   5.2 GB: 23-of-28   4.7 GB: 24-of-28   5.2 GB: 25-of-28   4.8 GB: 26-of-28   4.9 GB: 27-of-28   3.1 GB: 28-of-28
Supported Languagesen zh
Generates CodeYes
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwopus KAT Coder 35B Merged

Best Alternatives
Context / RAM
Downloads
Likes
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Tiel Coder 35B A3B MLX OQ4e0K / 21 GB5657
KAT Coder V2.5 Dev VL OQ8e Mtp0K / 38.4 GB2982
KAT Coder V2.5 Dev OQ6e0K / 28.5 GB1421
KAT Coder V2.5 Dev VL OQ4e Mtp0K / 21.5 GB1491
KAT Coder V2.5 Dev VL OQ6e Mtp0K / 30.2 GB513
Qwopus3.6 35B A3B Coder Bf160K / 69.9 GB2271
Qwopus3.6 35B A3B Coder 8bit0K / 37.8 GB7404
Qwopus3.6 35B A3B Coder 4bit0K / 20.5 GB6863
...der V2.5 Dev Vision OptiQ 4bit0K / 22.9 GB932
Note: green Score (e.g. "73.2") means that the model is better than OliviaRossi/Qwopus-KAT-Coder-35B-Merged.