chatterbox-turbo-GGUF Text-to-Speech Model: 4GB+ VRAM, File List
Resemble AI’s Chatterbox-Turbo TTS model is now available in GGUF format, enabling low-latency, high-quality vo ...
chatterbox-GGUF 23-Language Multilingual TTS Model: 4GB+ VRAM
Resemble AI’s 23-language TTS model Chatterbox Multilingual V3 is now available in GGUF format for llama.cpp.
Qwen3-30B-A3B-MoE-SAE: 80GB+ VRAM
ByteDance-Seed has released Sparse AutoEncoders (SAE) for the Qwen3-30B-A3B model, designed to interpret MoE expert b ...
Phonon: A Lightweight, Fully On-Device Text-to-Speech Model
Technical details for Phonon, a 65MB-75MB text-to-speech model capable of running entirely offline on mobile, PC, and ...
MetricTrail: File List
NVIDIA has released MetricTrail 1.0, a tool for estimating camera trajectories and absolute metric depth from long RG ...
Unsloth v0.1.915-beta Released with Browser Use & Qwen3.8
Unsloth v0.1.915-beta introduces Browser use, Qwen3.8 support, memory reductions, and enhanced local training feature ...
Ripple-65B-Preview Agentic Coding-Focused Dense Model: 32GB+ VRAM
Ricursive Intelligence has released Ripple-65B Preview, a 65B dense model supporting a 1M context length and trained ...
llama.cpp v0.9.0 Released: FP8 Quantization and More
llama.cpp v0.9.0 is released, featuring OCP FP8 E4M3 quantization support, KV cache improvements, multimodal updates, ...
Kimi-K3.1-Pro 1M-Context Multimodal Agent Model: ~1128GB Memory
Moonshot AI has released Kimi K3.1 Pro, an open-weight native multimodal agent model with 2.8T total parameters and a ...
GGML v0.29.0 Released: Multi-Node Tensor Parallelism and More
GGML v0.29.0 is released with initial support for multi-node tensor parallelism, OCP FP8 E4M3, new flash attention op ...