Snowball-67B-A2B-10T-Mixed-RLVR2-Async-Step146

open-athena/Snowball-67B-A2B-10T-Mixed-RLVR2-Async-Step146

Reinforcement Learning67.1B parameters
Tracked by OpenModelStats since September 23, 2026View on Hugging Face ↗
Downloads 30D
10
Total downloads
10
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
67.1B
Last source update
Sep 23, 2026

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-23. Charts appear as daily observations accumulate.

Overview

Snowball-67B-A2B-10T-Mixed-RLVR2-Async-Step146 is a reinforcement learning model published by open-athena. OpenModelStats has tracked the model since Sep 23, 2026, most recently observing it Sep 24, 2026.

Published
Sep 23, 2026
Last updated
Sep 23, 2026
Library
—
License
—
Task
Reinforcement Learning
Parameters
67,078,882,816
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsgrug_moereinforcement-learningrlvrasynchronous-rlmixture-of-expertsmegatronbase_model:open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.11base_model:finetune:open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.11region:us

Publisher

open-athenaView publisher statistics →

Derived from open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.11 (reported by the source; parent not yet tracked).

Similar models

Models similar to Snowball-67B-A2B-10T-Mixed-RLVR2-Async-Step146
ModelDL 30D
jtd-d5-69-30Blaion42
jtd-d3-60-30Blaion38
jtd-d0-69-30Blaion38
jtd-d2-20-30Blaion35
jtd-d4-34-30Blaion34
jtd-d1-18-30Blaion33