754B MoE scale
Safetensors metadata reports 753,910,024,032 parameters, described in the card text as 754B parameters.
Open Source Model Profile · zai-org
GLM-5.1-FP8
GLM-5.1-FP8 is a 754B-parameter GLM MoE text-generation model from zai-org. Card data records MIT licensing, and hub tags record FP8, Transformers, and Safetensors support.
- Publisher
- zai-org
- Task
- text-generation
- Model type
- glm_moe_dsa
- License
- mit
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
GLM-5.1-FP8 is published by zai-org as a GLM MoE text-generation model. The captured configuration identifies GlmMoeDsaForCausalLM with model type glm_moe_dsa, and Safetensors metadata reports 753,910,024,032 parameters. According to the model card text, the listing shows 754B parameters with F32, BF16, and F8_E4M3 tensor types.
Recorded capabilities
FP8 and mixed-precision listing
Hub tags record fp8, and the card text lists F32, BF16, and F8_E4M3 tensor types.
MIT license
Card data records mit, with hub tags repeating a license:mit entry.
Publisher access path
According to the model card, API services are available on the Z.ai API platform, with chat.z.ai availability described as coming.
Use cases in the source record
- Conversational text-generation work through the Transformers stack and the Z.ai API platform named in the model card.
- FP8-precision deployment experiments where the recorded fp8 tag and mixed tensor-type listing are relevant.
Limitations and unknowns
- No extracted benchmark scores were included in this record despite an eval-results tag; comparative performance is unknown.
- No context-window value, VRAM requirement, or throughput detail was extracted.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: zai-org/GLM-5.1-FP8
Captured: Unknown. Processed: 2026-09-07T19:36:04.461705+00:00.
GLM-5.1-FP8 👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.1 blog and GLM-5 Technical report . 📍 Use GLM-5.1 API services on Z.ai API Platform. 🔜 GLM-5.1 will be available on chat.z.ai in the coming days. [ Paper ] [ GitHub ] Introduction GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks). But the most meaningful leap goes beyond first-pass performance. Prev…
F001F002F003F004F005F006F007F008F009F010F012F013F014F015