APEX Quants (GGUF) Collection MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 24 items • Updated about 5 hours ago • 47
Nemotron-Cascade 2 Collection Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation • 4 items • Updated 7 days ago • 48
Running Featured 76 Cohere Transcribe WebGPU ⚡ 76 Run Cohere Transcribe locally in your browser on WebGPU.
Running Featured 75 Nemotron 3 Nano WebGPU ⚛ 75 A compact reasoning-capable model running in your browser.