b200
GLM-5.3-Flash-NVFP4-B200-hybridcapsd-less-humaneval-opc-marin-8b-base-code_less_b2000_s0capsd-less-ultra-opc-marin-8b-base-code_less_b2000_s0capsd-less-fast-opc-marin-8b-base-code_less_b2000_s0capsd-less-ultra-humaneval-opc-marin-8b-base-code_less_b2000_s0capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_cap_b2000_s0capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_ppl_b2000_s0capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b2000_s0
Datasets
All datasets matching “b200”ai_b200marin-qwen36-nemosci-terminus2-b200-parity-configsmarin-qwen36-nemosci-terminus2-b200-parity-artifacts
Marin Qwen3.6 and Nemosci Terminus-2 parity artifacts
This repository contains the deduplicated Harbor outputs, trajectories, operational evidence, and analysis for three Terminus-2 parity evaluations of Qwen3.6-35B-A3B and Nemosci Qwen3-32B on CoreWeave GB200 GPUs.
Each model and benchmark is packaged separately:
Archive
SHA-256
qwen3.6-dev-set-v2.tar.zst
884f78227e9838b9e762a46ec769141a1369b4b036792e6f196c07f8ab9ac465
qwen3.6-swebench.tar.zst… See the full description on the dataset page: https://huggingface.co/datasets/laion/marin-qwen36-nemosci-terminus2-b200-parity-artifacts.b200-profiling-vaeDr.Sparse-GPT56Luna-eval-b200-rl562-spgemm
Dr.Sparse — GPT-5.6 Luna SpGEMM eval on the 562-matrix pool
Snapshot state: complete (generated 2026-09-19 08:03 UTC)
phase
results
explore (3 branches x 5 iterations)
1686 / 1686
exploit (top-2 branches x 10 iterations)
1124 / 1124
matrices covered
562 / 562
What this is
Tree-search SpGEMM kernel optimization over the 562 matrices of
KinGeorge/Dr.Sparse-RL-train-562,
run on NVIDIA B200 (sm_100) and scored against cuSPARSE.
Model:… See the full description on the dataset page: https://huggingface.co/datasets/DiogenesChen122/Dr.Sparse-GPT56Luna-eval-b200-rl562-spgemm.moe-routing-profiling-b200