Autotrain compatible Conversational Endpoints compatible Multilingual Qwen3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Kwaipilot/KAT-Dev
KAT Dev Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
KAT Dev Parameters and Internals
| LLM Name | KAT Dev |
| Repository 🤗 | https://huggingface.co/Kwaipilot/KAT-Dev |
| Model Size | 32.8b |
| Required VRAM | 65.8 GB |
| Updated | 2025-09-15 |
| Maintainer | Kwaipilot |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.52.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to KAT Dev
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| XBai O4 | 40K / 65.6 GB | 1164 | 194 |
| M3 Agent Control | 40K / 65.5 GB | 449 | 48 |
| Shuttle 3.5 | 40K / 65.8 GB | 1098 | 44 |
| Others Second Stage | 40K / 131.6 GB | 16 | 0 |
| DeepSWE Preview Bf16 Mlx | 40K / 65.2 GB | 19 | 0 |
| XBai O4 8bit | 40K / 34.9 GB | 51 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than Kwaipilot/KAT-Dev .
Rank the KAT Dev Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51387 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124