GLM 5.2 504B — REAP keep 168, Router KD recovered (NVFP4) A 34% expert pruned GLM 5.2 that holds parity with the full unpruned model on a well powered real world eval — recovered by training only the router gates (0.016% of params), and quantized to NVFP4 for 8×B200 class serving. This is the flagship cut of the GLM 5.2 REAP series — the largest and highest fidelity, a strict superset of the earlier (now retired) 481B / 469B cuts. 📄 Full technical report: REPORT.md — the complete study (methods, the n=50→n=2000 correction, the significance stats, the GGUF DSA indexer surgery, negative results, and the free sampler fix). size. Coding benchmark results These scores are for 0xSero/GLM 5.2 504B (REAP keep 168 + Router KD, NVFP4) served through an OpenAI compatible endpoint. Benchmark Score Notes : Terminal Bench 2.1 full 89 70.5% Locked 89 task board faithful config, 5 attempts, terminus 2 , reasoning effort=max , temperature 1.0. Aider Polyglot 90.1% Aggregate language score across Python, JavaScript, Java, C++, Go, and Rust. Aider Polyglot language breakdown FULL is the unpruned GLM 5.2 baseline. REAP is this 504B REAP + Router KD checkpoint. Scores are percentages. Language FULL RE…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy