Model reference · open weights
GLM-5.2 is an open-weight language model from zai-org, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
GLM-5.2 👋 Join our <a href="https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/wechat.png" target="blank"WeChat</a or <a href="https://discord.gg/QR7SARHRxK" target="blank"Discord</a community. 📖 Check out the GLM-5.2 <a href="https://z.ai/blog/glm-5.2" target="blank"blog</a and GLM-5 <a href="https://arxiv.org/abs/2602.15763" target="blank"Technical report</a. 📍 Use GLM-5.2 API services on <a href="https://docs.z.ai/guides/llm/glm-5.2"Z.ai API Platform. </a 🔜 Try GLM-5.2 <a href="https://chat.z.ai"here</a. [<a href="https://huggingface.co/papers/2602.15763" target="blank"Paper</a] [<a href="https://github.com/zai-org/GLM-5" target="blank"GitHub</a] Introduction We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include: - Solid 1M Context: A solid 1M-token context that stably sustains long-horizon work - Advanced Coding with Flexible Effort: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency - Improved Architecture: We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20% - Pure Open: An MIT open-source license — no regional limits, technical access without borders Benchmark Serve GLM-5.2 Locally GLM-5.2 supports deployment with the following frameworks. Feel free to try them out: - SGLang (v0.5.13.post1+) — see cookbook - vLLM (v0.23.0+) — see recipes - Transformers (v0.5.12+) — see transformers docs - KTransformers (v0.5.12+) — see tutorial - Unsloth (v0.1.47-beta+) — see guide - For deployment on the Ascend NPU platform, inference frameworks such as vLLM-Ascend, xLLM and SGLang are supported — see here. Footnote Humanity’s Last Exam (HLE) & other reasoning tasks: We use sampling parameters of temperature=1.0, topp=0.95 for evaluation. We evaluate with a maximum generati
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | zai-org |
|---|---|
| Type | Language models |
| Parameters (lead) | 753.3B |
| Context | 1024k tokens |
| Variants | 2 |
| Runs with | transformers |
| Released | 2026-06-16 |
| Popularity | 1.9M downloads / month |
| Likes | 5,061 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys glm-5-2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (glm-5-2 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"glm-5-2","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗