gpt-oss-20b
رسمي · MXFP4 · safetensors
اجرا چاپېریال تایید شوی: Transformers
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|---|---|---|---|
| MXFP4 | safetensors | 4 | رسمي | اجرا چاپېریال تایید شوی |
GPT-OSS · عمومي · GPT-OSS
GPT-OSS 20B is a current General release in the GPT-OSS family, certified from its immutable official source revision.
GPT-OSS 20B is an official self-hostable OpenAI release in the GPT-OSS General track. It uses GptOssForCausalLM, carries 21B / 3.6B MoE, supports a verified context window of 131,072 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.
GPT-OSS 20B uses GptOssForCausalLM with 21B / 3.6B MoE. The stored architecture profile records 24 layers, hidden width 2880, 64 attention heads and a 131,072 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 · MXFP4 · safetensors
اجرا چاپېریال تایید شوی: Transformers
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|---|---|---|---|
| MXFP4 | safetensors | 4 | رسمي | اجرا چاپېریال تایید شوی |
Use only the listed transformers 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 ارزښت له مخې غوره سپارښتنه
80 GB ټول VRAM · nvswitch
59.27 GB اضافي ظرفیت · شته
USD ۱٬۸۶۰ / میاشتد عملي انتخابونو تر ټولو ټیټ لګښت
80 GB ټول VRAM · pcie
59.27 GB اضافي ظرفیت · محدود ظرفیت
USD ۱٬۵۷۹ / میاشتتر ټولو لوړ فعالیت
141 GB ټول VRAM · nvswitch
120.27 GB اضافي ظرفیت · محدود ظرفیت
USD ۲٬۳۴۵ / میاشتThe full 21B 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.
GPT-OSS 20B is published under apache-2.0. 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.
GPT-OSS 120B, gpt-oss-120b-Eagle3-v3, granitelib-rag-gpt-oss-r1.0
د سرچینې revision: 0092e0d9951eb4f12c2a37d27e03f6c2688cb749e08312cd3145232e3b737168
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.
The stored commercial classification is Commercial Use Allowed. Consult the official apache-2.0 terms for the final obligations.
وروستی تایید: 2026-09-03