Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 140
brabooObrabo/Kimi-Linear-48B-A3B-Instruct-MXFP4-GS32-MLX Text Generation • 49B • Updated Nov 8, 2025 • 191 • 2
brabooObrabo/Kimi-Linear-48B-A3B-Instruct-MXFP4-GS32-MLX Text Generation • 49B • Updated Nov 8, 2025 • 191 • 2
brabooObrabo/kanana-1.5-8b-instruct-2505-MXFP4-GS32-MLX Text Generation • 2B • Updated Oct 7, 2025 • 21
brabooObrabo/kanana-1.5-2.1b-instruct-2505-MXFP4-GS32-MLX Text Generation • 0.4B • Updated Oct 7, 2025 • 16
brabooObrabo/kanana-1.5-2.1b-instruct-2505-MXFP4-GS32-MLX Text Generation • 0.4B • Updated Oct 7, 2025 • 16
brabooObrabo/kanana-1.5-8b-instruct-2505-MXFP4-GS32-MLX Text Generation • 2B • Updated Oct 7, 2025 • 21
brabooObrabo/Qwen3-4B-Instruct-2507-MLX-4bit-GS32-embed-8bit-GS32 Text Generation • 0.8B • Updated Oct 7, 2025 • 48
thunder-research-group/SNU_Thunder-synthetic-instruction-following Viewer • Updated Jun 13, 2025 • 422k • 39 • 2
gpt-oss Collection Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 436
brabooObrabo/Qwen3-4B-Instruct-2507-MLX-4bit-GS32-embed-8bit-GS32 Text Generation • 0.8B • Updated Oct 7, 2025 • 48