LLM EXPLORER 57,252 MODELS INDEXED

KAT Dev 72B Exp FP8 by Kwaipilot

By Kwaipilot · 13 downloads
HF Repo ↗ Copy URL

KAT Dev 72B Exp FP8 is an open-source language model by Kwaipilot. Features: 72b LLM, VRAM: 75.5GB, Context: 156K, License: apache-2.0, LLM Explorer Score: 0.2.

  Compressed-tensors   Conversational   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Kwaipilot/KAT-Dev-72B-Exp-FP8 

KAT Dev 72B Exp FP8 Parameters and Internals

LLM NameKAT Dev 72B Exp FP8
Repository 🤗https://huggingface.co/Kwaipilot/KAT-Dev-72B-Exp-FP8 
Model Size72b
Required VRAM75.5 GB
Updated2026-08-08
MaintainerKwaipilot
Model Typeqwen2
Model Files  4.9 GB: 1-of-16   4.8 GB: 2-of-16   4.9 GB: 3-of-16   4.8 GB: 4-of-16   4.9 GB: 5-of-16   4.8 GB: 6-of-16   4.9 GB: 7-of-16   4.8 GB: 8-of-16   4.9 GB: 9-of-16   4.8 GB: 10-of-16   4.9 GB: 11-of-16   4.8 GB: 12-of-16   4.9 GB: 13-of-16   4.8 GB: 14-of-16   4.9 GB: 15-of-16   2.7 GB: 16-of-16
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length160000
Model Max Length160000
Transformers Version4.55.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to KAT Dev 72B Exp FP8

Best Alternatives
Context / RAM
Downloads
Likes
...R10528DistillQwen 72B Preview3195K / 146 GB87
Qwen2.5 72B128K / 145.5 GB13708101
Ultiima 72B128K / 146.1 GB513
Homer V1.0 Qwen2.5 72B128K / 146.1 GB146
Ultiima 72B V1.5128K / 146.1 GB250
EVA Qwen2.5 72B V0.2128K / 146 GB15922
Qwen2 72B128K / 145.5 GB18480199
AceInstruct 72B128K / 146 GB8818
...n2.5 72B 2x Instruct TIES V1.0128K / 146.1 GB551
Dolphin 2.9.2 Qwen2 72B128K / 146 GB1515162
Note: green Score (e.g. "73.2") means that the model is better than Kwaipilot/KAT-Dev-72B-Exp-FP8.