XingChen-AGI/Xing4.0-29B-A4B-GGUF
Text Generation • 31B • Updated • 8.33k • 154
AI & ML interests
XingChen-AGI is the open-source organization, dedicated to building agent-era large language models. Our flagship Xing4.0-29B-A4B is a 29B MoE model with only 4B activated parameters, natively supporting 256K context (extensible to 512K). With 4-bit quantization, it runs on a single consumer GPU (~15GB VRAM) and scores 93.52 on SuperCLUE Agent benchmark.
Recent Activity
View all activity
Version of vLLM/SGLang
3
#3 opened 4 days ago
by 
hahajinbu
training data knowledge cutoff
1
#10 opened 3 days ago
by 
khtsly
Minimum number of A100/H100 GPUs to serve Xing4.0-29B-A4B at full 256K context?
2
#9 opened 4 days ago
by 
rtudriny
wen Xing5.0?
🚀 2
1
#4 opened 4 days ago
by 
21g
Questions on safety alignment approach
1
#7 opened 4 days ago
by 
mavis8368
Chinese
2
#3 opened 4 days ago
by 
apathy-exe
On par with Qwen3.6 35B for thinking mode; slightly weaker without thinking. Advice?
1
#5 opened 4 days ago
by 
springbarley
Version of vLLM/SGLang
3
#3 opened 4 days ago
by hahajinbu
文本输出质量比同等规模的Qwen好
1
#1 opened 6 days ago
by 
chinanet-v1
Any plans for a larger Xing4.0 model?
🚀 1
1
#2 opened 4 days ago
by 
summergrove
Question regarding active parameters, VRAM requirements
1
#6 opened 4 days ago
by 
LolerPanda
Looking forward to a smaller Q4 version
2
#1 opened 7 days ago
by 
jian2023
xiongji
updated a
model 4 days ago
GSQ-RCO quants
3
#2 opened 7 days ago
by 
weather11
xcc
updated 2
models 6 days ago
xiongji
published 3
models 7 days ago