DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 18 days ago • 219
Running 98 The ultimate guide to multi-harness RL 🔀 98 Train open models with RL inside real agent harnesses
Decision models Collection GGUF decision models for the /v1/systemone API in llama.cpp • 6 items • Updated 2 days ago • 14
Decision models Collection GGUF decision models for the /v1/systemone API in llama.cpp • 6 items • Updated 2 days ago • 14
Running on Zero Agents 174 Viggle Turbo for Qwen-Image-2.1 ⚡ 174 6-step Qwen-Image-2.1, T2I + editing, vs-base comparison
perplexity-ai/pplx-embed-v2-context-9b-preview Feature Extraction • 8B • Updated 4 days ago • 429 • 52