GLM-5.3

Listed on the provider's own model-list page, not yet hand-verified into AI Squawk's model reference — some fields below may be unknown until it is. full model reference

unknown · released unknown · other · announcement · weights

Price

unknown — not published, or the API model id isn't known yet.

priced on 3 hosts

Context window

unknown

Rate limits

not published as a table by this provider.

Retirement

no retirement announced.

Runs on

Ollama · ollama pull glm-5.3 · library entry

Latest mentions

RELEASE GLM-5.3 Now Running on SambaCloud — GLM-5.3 is Z.ai's flagship model for complex software engineering and long-horizon agent tasks. · 2d ago
RESEARCH [P] NKI layer megakernels for GLM-5.3-Flash on AWS Trainium2: where a decode step's time went, and what we changed [P] — We wrote an inference engine for AWS Trainium2 that serves GLM-5.3-Flash (320B MoE, 1M-token context) on one trn2.48xlarge, and… · 9d ago
TOOLING [Doc] sgl-router: Add GLM-5.3-Flash and DeepSeek-V4.1-Flash deployment examples — · 18d ago
TOOLING Getting started with GLM-5.3 on Runpod's public endpoint — GLM-5.3 is now on Runpod's public endpoints at a lower price than elsewhere. · 22d ago
RELEASE Z.ai GLM-Legal Beats Claude Fable 5 and Kimi K3 on Harvey LAB — Z.ai’s GLM-Legal is a legal AI model built on GLM-5.3-Flash. · 32d ago
BUSINESS Last week some of South Korea's biggest banks were hit by a cyberattack. We now know the entire hack may have been done by a single person. He used a combined stack of an open-source AI penetration tool named ARTEX, DeepSeek v4.1-Flash, GLM-5.3, Grok 4.6, and Claude Code (CrowdStrike) — CrowdStrike Intelligence identified infrastructure associated with a targeted campaign against South Korean financial institutions that… · 37d ago
TOOLING We’re using GLM-5.3 Flash instead of frontier models on a massive production codebase — At my company, we’re using GLM-5.3 Flash internally for software engineering work, and I’ve been genuinely impressed by it. · 39d ago
RESEARCH A benchmark for LLMs playing Civilization V. GLM-5.3 is ahead of Opus-5.5, and Qwen-3.8-27B holds up surprisingly well. — A while ago, I posted here getting OSS-120B and GLM-4.6 playing full games of Civilization V. · 39d ago
TOOLING Two ~300B MoE models, each on ONE 128 GB mini PC (AMD Strix Halo): GLM-5.3-Flash at ~580 tok/s prefill, MiMo-V2.6-Flash up to 44 tok/s decode. EXL3 weights + open ROCm engine — We built an engine, Kyojin, on top of ExLlamaV3 for Strix Halo (gfx1151, ROCm), and packed two 300B-class MoE models so each fits one 128… · 42d ago
TOOLING add GLM-5.3-Flash (GLM5-Next) support by timkhronos · Pull Request #27773 · ggml-org/llama.cpp — Add support for GLM -5.3-flash a 320B hybrid model, supporting both text and vision. · 45d ago
BUSINESS Anthropic just dropped the greatest advertisement for GLM ever. — GLM-5.3 can autonomously build end-to-end cyber exploits, but unlike other frontier models, it was released without meaningful safeguards… · 45d ago
RESEARCH GLM-5.3 and the Spread of Advanced Cyber Capabilities \ Anthropic — GLM-5.3 can autonomously build end-to-end cyber exploits, but unlike other frontier models, it was released without meaningful safeguards… · 45d ago
RELEASE Aikido Security Releases Altar-1: An Open-Weight Security Model Pruned From GLM-5.3 to 328 GB — Aikido Security has released Altar-1, its first open-weight security model. · 50d ago
TOOLING Open Interpreter 0.0.44 — Models Add source-generated GLM-5.3 and GLM-5.3-Flash picker entries for Z.AI Coding Plan, Zhipu AI, and Zhipu AI… · 60d ago
RELEASE Latest open artifacts (#24): Motif-3, GLM-5.3, Hy4-preview and open model licenses — The open model ecosystem continues to expand in its breadth · 67d ago
RESEARCH (untitled) — We ran 900 DeepSWE rollouts on GLM-5.3 and GLM-5.3 Flash. · 78d ago
TOOLING v0.7.0.post1: feat(GLM): add native GLM-5.3-flash support (#2173) — feat: support SwiGLU limit for block FP8 experts … · 80d ago
RESEARCH GLM-5.3 vs. Claude Fable 5 on DeepSWE: Cost, Coding, and Routing — We ran 904 DeepSWE rollouts on GLM-5.3 and Claude Fable 5. · 85d ago
RESEARCH GLM-5.3 vs. GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing — We ran 904 DeepSWE rollouts on GLM-5.3 and GPT-5.6 Sol. · 85d ago
RESEARCH GLM-5.3: How Chinese labs keep stride with the frontier — Hint: It’s really not a distillation story. · 91d ago