Meta Releases Muse Spark Open: Multimodal MoE Model
Meta has reportedly released Muse Spark Open, an 816B parameter multimodal Mixture-of-Experts model supporting text, ...
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16: 80GB+ VRAM, GGUF Builds
Explore NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16, a full-precision vision-language model with a hybrid architectur ...
ggml v0.27.0 Released with Tensor-Parallel RPC and Major Speedups
ggml v0.27.0 is out, featuring major RPC updates, tensor-parallel server mode, and extensive performance boosts acros ...
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4: ~84GB Memory
Explore NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4, an NVFP4 quantized vision-language model with 120B total parame ...
Jais-3-0.9B-GGUF Bilingual Dense Model: 4GB+ VRAM
The GGUF quantized version of Jais-3-0.9B, a 0.9B parameter bilingual model specializing in Arabic and English, has b ...
Jais-3-3.7B-GGUF 512K Context Language Model: 4GB+ VRAM
IFM has released IFM/Jais-3-3.7B-GGUF, a GGUF version of the Arabic-English open-weight model supporting a 512K conte ...
Jais-3-MoVA-36B-A4B-GGUF Text Generation Model: 32GB+ VRAM
Explore the GGUF release of Jais-3-MoVA-36B-A4B, an Arabic and English MoE language model with 512K context, running ...
Jais-3-7B-GGUF Arabic and English 7B Reasoning Model: 8GB+ VRAM
IFM has released Jais-3-7B-GGUF on Hugging Face, a 7B decoder-only model optimized for Arabic and English agent tasks ...
Magnitude @magnitudedev/cli@0.2.9 Released
Magnitude 0.2.9 is released, featuring server mode setup, web UI support, Claude Code connection, and performance imp ...
Jais-3-32B-GGUF Arabic and English 32B Dense Model: 24GB+ VRAM
IFM releases Jais-3-32B-GGUF for local execution via llama.cpp. Explore specifications, performance, and hardware req ...