GLM-4.5-FP8
رسمي · FP8 · safetensors
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|
GLM · عمومي · glm-4-5
GLM-4.5-FP8: ځانګړنې، د GPU اړتیاوې، کوربهتوب او ځایپرځای کول
GLM-4.5-FP8 is a recent General release in the GLM family, certified from its immutable official source revision.
یوازې د مرجع لپاره
دا ماډل پرتله کړئ
ټول پارامېټرونهجوړوونکي دا معلومات نه دي خپاره کړي.
فعال پارامېټرونهDense ماډل
د context کړکۍN/A / نېغه پرتله نه شي کېدای
د نسخې وضعیتوروستی · وروستی
معماري
موداليټيګانېمتن
جوازmit
د ځایپرځای کولو حالتیوازې د مرجع لپاره
سوداګریز وضعیتسوداګریزه کارونه اجازه لري
د خپرېدو نېټه
معماري، پیاوړتیاوې او کارونې
GLM-4.5-FP8 is an official self-hostable Z.ai release in the GLM General track. It uses The manufacturer has not published this information., carries The manufacturer has not published this information., supports a verified context window of 0 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-4.5-FP8 uses The manufacturer has not published this information. with The manufacturer has not published this information.. The stored architecture profile records layers, hidden width , attention heads and a 0 ټوکن context ceiling where the official configuration publishes those fields.
Verified The manufacturer has not published this information. architecture
Official checkpoint and بهیر evidence
Official FP8 checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
تایید شوي checkpoint-ونه او quantization-ونه
یوازې د سرچینې له خوا تصدیق شوې کره بڼې چې له دې نسخې سره تړلې دي، ښودل کېږي.
سپارښتل شوی هارډوېیر
Use only the listed certified 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.
یوازې د مرجع لپاره
The official license permits commercial use; its obligations still apply.
د جواز او خپل کوربهتوب ملاحظات
The full 0B 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-4.5-FP8 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.
بدیلونه او همنسله بڼې
GLM-5.3, GLM-5.2-NVFP4, GLM-5-NVFP4, GLM-5.1-NVFP4, GLM-4.7-NVFP4, GLM-5.2-FP8, GLM-5.1-FP8, GLM-5-FP8, GLM-4.7-FP8, GLM-5.2, GLM-5.1
د نسخو مهالوېش
zai/glm/glm-45-fp8
د سرچینې جزئیات
د سرچینې revision: e8f310639bb36f7e90459d702cea3d887fea530601eb38d3a2fe52212f597455
ډېرې پوښتل شوې پوښتنې
How much VRAM does GLM-4.5-FP8 require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible د اجرا چاپېریال configurations.
Which د اجرا چاپېریالونه ملاتړ GLM-4.5-FP8?
No د اجرا چاپېریال is presented as supported until upstream evidence is verified.
Can GLM-4.5-FP8 be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official mit terms for the final obligations.
رسمي مراجع
وروستی تایید: 2026-09-04