Snowball-67B-A2B-5.7T-Mixed-RLVR-Step38

open-athena/Snowball-67B-A2B-5.7T-Mixed-RLVR-Step38

Reinforcement Learning67.1B parameters
Tracked by OpenModelStats since September 22, 2026View on Hugging Face ↗
Downloads 30D
14
Total downloads
14
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
67.1B
Last source update
Sep 23, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-22. Charts appear as daily observations accumulate.

Overview

Snowball-67B-A2B-5.7T-Mixed-RLVR-Step38 is a reinforcement learning model published by open-athena. OpenModelStats has tracked the model since Sep 22, 2026, most recently observing it Sep 23, 2026.

Published
Sep 22, 2026
Last updated
Sep 23, 2026
Library
—
License
—
Task
Reinforcement Learning
Parameters
67,078,882,816
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsgrug_moereinforcement-learningrlvrmixture-of-expertsmegatronbase_model:laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888base_model:finetune:laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888region:us

Publisher

open-athenaView publisher statistics →

Derived from laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888 (reported by the source; parent not yet tracked).

Similar models

Models similar to Snowball-67B-A2B-5.7T-Mixed-RLVR-Step38
ModelDL 30D
jtd-d5-69-30Blaion42
jtd-d0-69-30Blaion38
jtd-d3-60-30Blaion38
jtd-d2-20-30Blaion35
jtd-d4-34-30Blaion34
jtd-d1-18-30Blaion33