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

Xing4.0 29B A4B OR SFT requires approximately 62.9 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 OR SFT and how large is it?

Xing4.0 29B A4B OR SFT is developed by HITSZ-TMG, 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 OR SFT?

Xing4.0 29B A4B OR SFT 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 OR SFT by HITSZ-TMG — VRAM 62.9GB, 256K context

Name: Xing4.0 29B A4B OR SFT
Author: HITSZ-TMG

Xing4.0 29B A4B OR SFT is an open-source language model by HITSZ-TMG. Features: 29b LLM, VRAM: 62.9GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.32.

Base model:finetune:xingchen-a... Base model:xingchen-agi/xing4.... Code-generation Conversational Custom code En Finetuned Gurobi Mathematical-programming Mla Moe Operations-research Optimization Pyomo Region:us Safetensors Sft Sharded Tensorflow Xing4 0 Zh

Model Card on HF 🤗: https://huggingface.co/HITSZ-TMG/Xing4.0-29B-A4B-OR-SFT

Xing4.0 29B A4B OR SFT Parameters and Internals

LLM Name	Xing4.0 29B A4B OR SFT
Repository 🤗	https://huggingface.co/HITSZ-TMG/Xing4.0-29B-A4B-OR-SFT
Base Model(s)	XingChen-AGI/Xing4.0-29B-A4B XingChen-AGI/Xing4.0-29B-A4B
Model Size	29b
Required VRAM	62.9 GB
Updated	2026-09-22
Maintainer	HITSZ-TMG
Model Type	xing4_0
Model Files	1.2 GB: 1-of-41 0.3 GB: 2-of-41 1.5 GB: 3-of-41 1.5 GB: 4-of-41 1.5 GB: 5-of-41 1.5 GB: 6-of-41 1.5 GB: 7-of-41 1.5 GB: 8-of-41 1.5 GB: 9-of-41 1.5 GB: 10-of-41 1.5 GB: 11-of-41 1.5 GB: 12-of-41 1.5 GB: 13-of-41 1.5 GB: 14-of-41 1.5 GB: 15-of-41 1.5 GB: 16-of-41 1.5 GB: 17-of-41 1.5 GB: 18-of-41 1.5 GB: 19-of-41 1.5 GB: 20-of-41 1.5 GB: 21-of-41 1.5 GB: 22-of-41 1.5 GB: 23-of-41 1.5 GB: 24-of-41 1.5 GB: 25-of-41 1.5 GB: 26-of-41 1.5 GB: 27-of-41 1.5 GB: 28-of-41 1.5 GB: 29-of-41 1.5 GB: 30-of-41 1.5 GB: 31-of-41 1.5 GB: 32-of-41 1.5 GB: 33-of-41 1.5 GB: 34-of-41 1.5 GB: 35-of-41 1.5 GB: 36-of-41 1.5 GB: 37-of-41 1.5 GB: 38-of-41 1.5 GB: 39-of-41 1.5 GB: 40-of-41 4.4 GB: 41-of-41
Supported Languages	en zh
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 OR SFT 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 OR SFT

Best Alternatives	Context / RAM	Downloads	Likes
Xing4.0 29B A4B	256K / 62.9 GB	7278	616
Xing4.0 29B A4B FP8	256K / 31.4 GB	185	95
Xing4.0 29B A4B 8bit MLX	256K / 31.4 GB	116	1
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 HITSZ-TMG/Xing4.0-29B-A4B-OR-SFT.