{"id":6182,"date":"2026-09-28T12:05:15","date_gmt":"2026-09-28T03:05:15","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/model-xingchen-agi-xing4-0-en\/"},"modified":"2026-09-28T12:10:39","modified_gmt":"2026-09-28T03:10:39","slug":"model-xingchen-agi-xing4-0-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-xingchen-agi-xing4-0-en\/","title":{"rendered":"Xing4.0 Guide: VRAM Requirements, GGUF Builds"},"content":{"rendered":"

Everything Local Model Watch has published about the Xing4.0<\/strong> family: 1 article(s) covering the base model and its fine-tunes, plus converted builds we tracked after publication. Memory requirements below are computed by this site from file sizes, not quoted from model cards. Part of our model family index<\/a>.<\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Base model(s)<\/td>\nXingChen-AGI\/Xing4.0-29B-A4B<\/a><\/td>\n<\/tr>\n
Publisher<\/td>\nChina Telecom (Xing, TeleChat)<\/a><\/td>\n<\/tr>\n
Parameters<\/td>\n31.2B<\/td>\n<\/tr>\n
License (model card)<\/td>\napache-2.0<\/td>\n<\/tr>\n
Smallest VRAM tier<\/td>\n24GB<\/td>\n<\/tr>\n
Articles<\/td>\n1<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Hardware Requirements<\/h2>\n

Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 31.2B parameters<\/p>\n

\n\n\n\n\n\n
Your VRAM<\/th>\nQuantization<\/th>\nFile size<\/th>\nEst. memory needed<\/th>\n<\/tr>\n<\/thead>\n
24GB (RTX 4090 \/ 3090, etc.)<\/td>\nIQ4_NL<\/td>\n18.7GB<\/td>\n22.5GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model’s authors. File sizes are measured from the converted build XingChen-AGI\/Xing4.0-29B-A4B-GGUF<\/a>. Compare with other models in our VRAM quick reference<\/a>. What the quantization names mean: glossary<\/a>.<\/em><\/p>\n

Can You Run It Locally?<\/h2>\n

Runs in Ollama, LM Studio and llama.cpp via a converted build.<\/strong><\/p>\n

The publisher ships safetensors, but XingChen-AGI\/Xing4.0-29B-A4B-GGUF<\/a> provides a GGUF build you can use.<\/p>\n

License \u2014 apache-2.0<\/code> (Commercial use allowed):<\/strong> Permits commercial use, modification and redistribution. Redistribution requires including the license and stating changes; includes a patent grant.<\/p>\n

Compression:<\/strong> the IQ4_NL build measures 5.15 bits per weight \u2014 about 32% the size of the original 16-bit weights, calculated by this site from the actual file sizes.<\/p>\n

Compiled by this site’s code from the published formats, converted builds we have found, and each engine’s own model registry. “Not found” means we have not seen such a build, not that none exists. License summaries are not legal advice \u2014 check the publisher’s original terms before relying on them.<\/em><\/p>\n

Quantized and Converted Variants<\/h2>\n
\n

\u2192 Scroll horizontally to see all columns<\/p>\n\n\n\n\n\n\n\n
Added<\/th>\nPublisher<\/th>\nFormat<\/th>\nRepository<\/th>\nSmallest VRAM tier (build, est. memory)<\/th>\n<\/tr>\n<\/thead>\n
2026-09-28<\/td>\nXingChen-AGI<\/td>\nGGUF (imatrix)<\/td>\nXingChen-AGI\/Xing4.0-29B-A4B-GGUF<\/a><\/td>\nIQ4_NL 22.5GB (fits in 24GB VRAM)<\/td>\n<\/tr>\n
2026-09-28<\/td>\nXingChen-AGI<\/td>\nFP8<\/td>\nXingChen-AGI\/Xing4.0-29B-A4B-FP8<\/a><\/td>\nFP8 37.1GB (fits in 48GB VRAM)<\/td>\n<\/tr>\n
2026-09-28<\/td>\nmlx-community<\/td>\nMLX<\/td>\nmlx-community\/Xing4.0-29B-A4B-OptiQ-4bit<\/a><\/td>\nMLX 4bit 23.0GB (fits in 24GB VRAM)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

File sizes of each build:<\/p>\n