clef-flash Vision-Language Model: Our Test Answers, 4GB+ VRAM
Explore the specifications, benchmarks, strengths, and hardware requirements of Clef-Flash, a 9B structured decision- ...
OpenJev-GGUF 27.4B Decision-Making Specialized Model: 24GB+ VRAM
Explore OpenJev-GGUF, a GGUF quantized open-weight decision-making model by ggml-org designed for structured choices ...
PixelUMM Multimodal Model: 24GB+ VRAM
Explore NVIDIA’s PixelUMM, an encoder-free multimodal model handling text, image, and video generation and unde ...
Alania Synthetic Speech TR: Turkish Speech Dataset Released
Explore alania-synthetic-speech-tr, a large-scale synthetic Turkish speech dataset for TTS and ASR training, includin ...
Testing OpenJev GGUF: A Tiny Model for Runtime Loaders
Explore tinyopenjev-for-testing-gguf, a miniature GGUF model by ggml-org designed for testing loader and runtime beha ...
clef Structured Decision-Making Model: 12GB+ VRAM, GGUF Builds
Cloudflare has released Clef, a 27B multimodal decision-making model based on Qwen3.8-27B. Learn about its specs, per ...
Unsloth v0.1.901-beta Released: Major LoRA Memory Reductions
Unsloth v0.1.901-beta is released, featuring massive LoRA memory reductions for 4-bit checkpoints, a desktop command ...
Magnitude: Up to 2x Faster Than llama.cpp Officially, 21x Slower on Our CPU
Magnitude is an open-source inference engine for AI agents that auto-optimizes kernels for hardware, beating llama.cp ...
Phonon-2 Speech Recognition Model: 4GB+ VRAM
Discover Phonon-2 by FermionResearch, an open-weight English ASR model offering high accuracy and low memory usage fo ...
LTX-2.5-22b-IC-LoRA-SDR-To-HDR Video Generation Model: File List
Lightricks has released LTX-2.5-22b-IC-LoRA-SDR-To-HDR, an IC-LoRA adapter for converting SDR videos to HDR using LTX ...