What are the hardware requirements for Xing4.0 29B A4B FP8?

Xing4.0 29B A4B FP8 requires approximately 31.4 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Xing4.0 29B A4B FP8 and how large is it?

Xing4.0 29B A4B FP8 is developed by XingChen-AGI, a model with 29b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Xing4.0 29B A4B FP8?

Xing4.0 29B A4B FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Xing4.0 29B A4B FP8 by XingChen-AGI — VRAM 31.4GB, 256K context

Name: Xing4.0 29B A4B FP8
Author: XingChen-AGI

Xing4.0 29B A4B FP8 is an open-source language model by XingChen-AGI. Features: 29b LLM, VRAM: 31.4GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.31.

Arxiv:2507.18013 Arxiv:2512.24157 Conversational Custom code Fp8 Region:us Safetensors Sharded Tensorflow Xing4 0

Model Card on HF 🤗: https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B-FP8

Xing4.0 29B A4B FP8 Parameters and Internals

LLM Name	Xing4.0 29B A4B FP8
Repository 🤗	https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B-FP8
Model Size	29b
Required VRAM	31.4 GB
Updated	2026-09-19
Maintainer	XingChen-AGI
Model Type	xing4_0
Model Files	1.1 GB: 1-of-41 0.1 GB: 2-of-41 0.7 GB: 3-of-41 0.7 GB: 4-of-41 0.7 GB: 5-of-41 0.7 GB: 6-of-41 0.7 GB: 7-of-41 0.7 GB: 8-of-41 0.7 GB: 9-of-41 0.7 GB: 10-of-41 0.7 GB: 11-of-41 0.7 GB: 12-of-41 0.7 GB: 13-of-41 0.7 GB: 14-of-41 0.7 GB: 15-of-41 0.7 GB: 16-of-41 0.7 GB: 17-of-41 0.7 GB: 18-of-41 0.7 GB: 19-of-41 0.7 GB: 20-of-41 0.7 GB: 21-of-41 0.7 GB: 22-of-41 0.7 GB: 23-of-41 0.7 GB: 24-of-41 0.7 GB: 25-of-41 0.7 GB: 26-of-41 0.7 GB: 27-of-41 0.7 GB: 28-of-41 0.7 GB: 29-of-41 0.7 GB: 30-of-41 0.7 GB: 31-of-41 0.7 GB: 32-of-41 0.7 GB: 33-of-41 0.7 GB: 34-of-41 0.7 GB: 35-of-41 0.7 GB: 36-of-41 0.7 GB: 37-of-41 0.7 GB: 38-of-41 0.7 GB: 39-of-41 0.7 GB: 40-of-41 3.6 GB: 41-of-41
Model Architecture	Xing4_0ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.14.1
Vocabulary Size	131072

Rank the Xing4.0 29B A4B FP8 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Xing4.0 29B A4B FP8

Best Alternatives	Context / RAM	Downloads	Likes
Xing4.0 29B A4B	256K / 62.9 GB	7278	616
Xing4.0 29B Intent	256K / 62.9 GB	3046	165
...ui Xing4.0 29B A4B Abliterated	256K / 62.9 GB	410	23
Xing4.0 29B A4B W8a8	256K / 31.8 GB	206	5
Xing4.0 29B A4B Finance SFT	256K / 62.9 GB	280	3
Xing4.0 29B A4B OR SFT	256K / 62.9 GB	219	2
Xing4.0 29B A4B 8bit MLX	256K / 31.4 GB	333	2
Xing4.0 29B A4B OptiQ 4bit	256K / 20.6 GB	178	2
Xing4.0 29B A4B GGUF	256K / 0.1 GB	14361	257
Xing4.0 29B A4B GGUF	256K / 0.1 GB	1085	5

Note: green Score (e.g. "73.2") means that the model is better than XingChen-AGI/Xing4.0-29B-A4B-FP8.