APEX Quants (GGUF) Collection MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) β’ 22 items β’ Updated 1 day ago β’ 36
microsoft/harrier-oss-v1-0.6b Feature Extraction β’ 0.6B β’ Updated 10 days ago β’ 18k β’ β’ 177
Nemotron-Cascade 2 Collection Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation β’ 4 items β’ Updated 2 days ago β’ 47
Running Featured 71 Cohere Transcribe WebGPU β‘ 71 Run Cohere Transcribe locally in your browser on WebGPU.
Running Featured 74 Nemotron 3 Nano WebGPU β 74 A compact reasoning-capable model running in your browser.