unsloth ships Meta's Muse-Spark-Open 816B-A42B multimodal weights in NVFP4
unsloth · hf · 2026-10-16
unsloth released Muse-Spark-Open-816B-A42B-NVFP4 on Hugging Face: Meta's Muse-series image-text-to-text multimodal model with a sparse MoE architecture (816B total / 42B active parameters), shipped in NVFP4 quantization with transformers/safetensors/pytorch support and a conversational template.
More from Models
- OpenAI blocks manual reset with 13% usage left: 'no reset needed right now' — AccomplishedSugar490 · 2026-10-23
- Meta's 816B Muse Spark Open scores 39, losing to 180B Qwen3.8-Flash-Next at 40 — BTA_Labs · 2026-10-23
- Gemini refuses to generate image in Docs, blames document size limit — viksit · 2026-10-23
- Dev jokes his true calling is telling everyone to try the latest DeepSeek — intellectronica · 2026-10-23
- SubQ Snap 1.1 ties for first on Artificial Analysis Decision Index with 384K context — ArtificialAnlys · 2026-10-23
- PolyAI unveils Dialog-RSN-1: audio-native voice model answering in under 300ms — matthen2 · 2026-10-23