MiniMax-M3
رسمي · BF16 · safetensors
اجرا چاپېریال تایید شوی: vLLM SGLang Transformers KTransformers
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|---|---|---|---|
| BF16 | safetensors | 16 | رسمي | اجرا چاپېریال تایید شوی |
MiniMax · عمومي · MiniMax M3
MiniMax M3 is a current General release in the MiniMax family, certified from its immutable official source revision.
MiniMax M3 is an official self-hostable MiniMax release in the MiniMax General track. It uses MiniMaxM3SparseForConditionalGeneration, carries 428B / 23B 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.
MiniMax M3 uses MiniMaxM3SparseForConditionalGeneration with 428B / 23B MoE. The stored architecture profile records 60 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: vLLM SGLang Transformers KTransformers
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|---|---|---|---|
| BF16 | safetensors | 16 | رسمي | اجرا چاپېریال تایید شوی |
رسمي · MXFP8 · safetensors
اجرا چاپېریال تایید شوی: Transformers vLLM SGLang KTransformers
| Precision / quantization | بڼه | بټونه | پر خپروونکي باور | د ځایپرځای کولو حالت |
|---|---|---|---|---|
| MXFP8 | safetensors | 8 | رسمي | اجرا چاپېریال تایید شوی |
Use only the listed vllm, sglang, transformers, 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.
سوداګریز حقونه نه دي تایید شوي، نو د دې خپرونې سوداګریزه سپارښتنه نه کېږي.
The full 428B 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.
MiniMax M3 is published under other. The release-scoped official license link and verification date are retained with the catalogue record.
ناڅرګند / د سپارښتنې وړ نه دی. سوداګریز حقونه نه دي تایید شوي، نو د دې خپرونې سوداګریزه سپارښتنه نه کېږي.
MiniMax M2.7, MiniMax M2.5, MiniMax M2.1
د سرچینې revision: 379adf789f3179a77837f6818a8b981c05678577dd940948d3bfc980bc622f4d
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 vllm, sglang, transformers, ktransformers.
The stored commercial classification is Unknown / Not Recommendable. Consult the official other terms for the final obligations.
وروستی تایید: 2026-09-03