8-bit 8bit Base model:metastonetec/xbai-o... Base model:quantized:metastone... Conversational Mlx Quantized Qwen3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/XBai-o4-8bit
XBai O4 8bit 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)
XBai O4 8bit Parameters and Internals
| LLM Name | XBai O4 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/XBai-o4-8bit |
| Base Model(s) | |
| Model Size | 32.8b |
| Required VRAM | 34.9 GB |
| Updated | 2025-09-21 |
| Maintainer | mlx-community |
| Model Type | qwen3 |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.51.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to XBai O4 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| KAT Dev | 128K / 65.8 GB | 286 | 3 |
| XBai O4 | 40K / 65.6 GB | 1037 | 194 |
| M3 Agent Control | 40K / 65.5 GB | 477 | 48 |
| Shuttle 3.5 | 40K / 65.8 GB | 1077 | 44 |
| Others Second Stage | 40K / 131.6 GB | 5 | 0 |
| DeepSWE Preview Bf16 Mlx | 40K / 65.2 GB | 15 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/XBai-o4-8bit .
Rank the XBai O4 8bit 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? 51507 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124