chiprook
← AI
AIOctober 21, 2026, 02:16

Muse Spark Open: 816B parameters and 700 GB VRAM to self-host

Meta released Muse Spark Open, an open-weight 816B-parameter MoE model with 42B active parameters and a 1M-token context. The NVFP4 build needs at least 700 GB of VRAM and BF16 needs 2 TB, while hosted API access costs $1.25 per million input tokens.

Muse Spark Open: 816B parameters and 700 GB VRAM to self-host
#Meta#MuseSparkOpen#OpenRouter
Read next
AI

AI Daily Digest October 17, 2026: Meta Opens 816B-Parameter Model

AI

Strata runs a 125B LLM on a gaming PC with 12 GB VRAM

AI

ISOM-R2 streams 1,055,402 tokens at 3.24 GB peak VRAM

AI

StepFun Step 5 Preview lands on OpenRouter with 600B parameters and 1M context