LLM EXPLORER 61,836 MODELS INDEXED

Xing4.0 29B A4B 8bit MLX by suzu89

By suzu89 · 116 downloads
HF Repo ↗ Copy URL

Xing4.0 29B A4B 8bit MLX is an open-source language model by suzu89. Features: 29b LLM, VRAM: 31.4GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  Arxiv:2512.24157   8-bit   8bit   Apple-silicon Base model:quantized:xingchen-... Base model:xingchen-agi/xing4....   Base model size:10b to 100b   Conversational   Custom code   Hyper-connections   Mla   Mlx   Moe   Quantization   Quantized   Region:us   Safetensors   Sharded   Telechat   Tensorflow   Xing   Xing4 0
Model Card on HF 🤗: https://huggingface.co/TokenAI-zer/Xing4.0-29B-A4B-8bit-MLX 

Xing4.0 29B A4B 8bit MLX Parameters and Internals

LLM NameXing4.0 29B A4B 8bit MLX
Repository 🤗https://huggingface.co/TokenAI-zer/Xing4.0-29B-A4B-8bit-MLX 
Model NameXing4.0-29B-A4B-8bit-MLX
Base Model(s)  XingChen-AGI/Xing4.0-29B-A4B   XingChen-AGI/Xing4.0-29B-A4B
Model Size29b
Required VRAM31.4 GB
Updated2026-09-21
Maintainersuzu89
Model Typexing4_0
Model Files  5.3 GB: 1-of-6   5.3 GB: 2-of-6   5.3 GB: 3-of-6   5.2 GB: 4-of-6   5.3 GB: 5-of-6   5.0 GB: 6-of-6
Quantization Type8bit
Model ArchitectureXing4_0ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassXing4_0Tokenizer
Padding Token<_pad>
Vocabulary Size131072

Best Alternatives to Xing4.0 29B A4B 8bit MLX

Best Alternatives
Context / RAM
Downloads
Likes
Xing4.0 29B A4B256K / 62.9 GB7278616
Xing4.0 29B A4B FP8256K / 31.4 GB18595
Xing4.0 29B A4B GGUF256K / 0.1 GB10855
Note: green Score (e.g. "73.2") means that the model is better than TokenAI-zer/Xing4.0-29B-A4B-8bit-MLX.