GLM · عمومي · GLM-5.2
GLM-5.2 is a recent General release in the GLM family, certified from its immutable official source revision.
GLM-5.2 is an official self-hostable Z.ai release in the GLM General track. It uses GlmMoeDsaForCausalLM, carries 744B / 40B MoE, supports a verified context window of 1,048,576 ټوکنونه, and exposes only source-certified checkpointونه and د اجرا چاپېریال combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
GLM-5.2 uses GlmMoeDsaForCausalLM with 744B / 40B MoE. The stored architecture profile records 78 layers, hidden width 6144, 64 attention heads and a 1,048,576 ټوکن context ceiling where the official configuration publishes those fields.
یوازې د سرچینې له خوا تصدیق شوې کره بڼې چې له دې نسخې سره تړلې دي، ښودل کېږي.
رسمي · BF16 · safetensors
اجرا چاپېریال تایید شوی: Transformers vLLM >=0.23.0 SGLang >=0.5.13.post1 KTransformers >=0.5.12
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|---|---|---|---|
| BF16 | safetensors | 16 | رسمي | اجرا چاپېریال تایید شوی |
رسمي · FP8 · safetensors
اجرا چاپېریال تایید شوی: Transformers vLLM >=0.23.0 SGLang >=0.5.13.post1 KTransformers >=0.5.12
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|---|---|---|---|
| FP8 | safetensors | 8 | رسمي | اجرا چاپېریال تایید شوی |
Use only the listed transformers, vllm, sglang, ktransformers د اجرا چاپېریال configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, د اجرا چاپېریال overhead, safety اضافي ظرفیت, GPU architecture and topology before ranking rentable and reference hardware.
د FusionPointAI په اوسني موجودي کې هېڅ مورد د دې کره checkpoint لپاره د اجرا چاپېریال، معمارۍ، جوړښت او حافظې ټول شرطونه نه پوره کوي. د نړۍ په کچه سازګار هارډوېیر لپاره اټکلکوونکی وکاروئ.
The full 744B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
GLM-5.2 is published under mit. The release-scoped official license link and verification date are retained with the catalogue record.
سوداګریزه کارونه اجازه لري. رسمي جواز سوداګریزه کارونه اجازه کوي؛ د جواز نور مکلفیتونه هم پر خپل ځای دي.
GLM-5.3, GLM-5.1, GLM-5
د سرچینې revision: cd87f2e073a9a24b8b0c54fe4919d5c80384a2529266dc8bb613833558d1a06f
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible د اجرا چاپېریال configurations.
Certified upstream د اجرا چاپېریال evidence is available for transformers, vllm, sglang, ktransformers.
The stored commercial classification is Commercial Use Allowed. Consult the official mit terms for the final obligations.
وروستی تایید: 2026-09-03
