Swift for HyperQwen — RTX 3090 benchmarks Collection Swift efficient reasoning + HyperQwen serving: three checkpoints compared on RTX 3090 task time, token use, throughput and quality. • 3 items • Updated 3 days ago
daavidhauser/Swift-1.5-Qwen3.8-27B-W4A16-HyperQwen Text Generation • 28B • Updated 3 days ago • 423 • 2
daavidhauser/Swift-1.5-Qwen3.8-27B-W4A16-HyperQwen Text Generation • 28B • Updated 3 days ago • 423 • 2
Swift for HyperQwen — RTX 3090 benchmarks Collection Swift efficient reasoning + HyperQwen serving: three checkpoints compared on RTX 3090 task time, token use, throughput and quality. • 3 items • Updated 3 days ago
daavidhauser/Swift-1.5-Qwen3.8-27B-W4A16-HyperQwen-INT4 Text Generation • 28B • Updated 3 days ago • 82
daavidhauser/Swift-1.5-Qwen3.8-27B-W4A16-HyperQwen-INT4 Text Generation • 28B • Updated 3 days ago • 82
view article Article Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident +2 hlarcher, XciD, raphael-gl, chris-rannou • Jul 27 • 507
Mistral Small 4 Collection A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated Mar 16 • 81