Unverified50% confidenceFactExact time
GLM 5.3 Flash is a model developed by Zai, previously appeared on OpenRouter under the name Oakies EFLA, and has processed trillions of tokens on domestic chips.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
GLM 5.3 Flash Local Test: Fitting a 320B Model into 4 RTX 3090s with 1-bit Quantization
bilibili四月的尾巴_10/13/2026
Related Entities
Related Claims
VerifiedZhipu AI has launched the GLM-5.3 Flash lightweight model.73% similarUnverifiedGLM-5.3 Flash relies entirely on domestically produced chips for training and inference, without depending on overseas AI chips such as those from NVIDIA.71% similarUnverifiedGLM-5.3 Flash took first place in the GDPVL AAVR test.67% similarUnverifiedGLM-5.3-Flash can now run on AMD MI355X and supports FP8/MXFP4 MoE and MTP speculative decoding.66% similarUnverifiedGLM-5.3-Flash 在国产AI芯片上规模化运行，搭配基于 SGLang 的专用推理引擎，声称端到端服务增益达到3倍。66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1035998API
curl https://kongchang.com/api/v1/knowledge/claims/1035998MCP
get_claim(id=1035998)