Model Card on HF 🤗: https://huggingface.co/ByteDance-Seed/M3-Agent-Control
M3 Agent Control 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)
M3 Agent Control Parameters and Internals
| LLM Name | M3 Agent Control |
| Repository 🤗 | https://huggingface.co/ByteDance-Seed/M3-Agent-Control |
| Model Size | 32.8b |
| Required VRAM | 65.5 GB |
| Updated | 2025-08-26 |
| Maintainer | ByteDance-Seed |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.53.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to M3 Agent Control
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| XBai O4 | 40K / 65.6 GB | 1875 | 192 |
| Shuttle 3.5 | 40K / 65.8 GB | 1138 | 44 |
| Others Second Stage | 40K / 131.6 GB | 23 | 0 |
| DeepSWE Preview Bf16 Mlx | 40K / 65.2 GB | 38 | 0 |
| XBai O4 8bit | 40K / 34.9 GB | 654 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than ByteDance-Seed/M3-Agent-Control .
Rank the M3 Agent Control 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? 50900 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124