open-athena/Snowball-67B-A2B-Chat-Aligned-Base-2026.10.22
Text Generation • 67B • Updated • 258
Chat-Aligned Bases
Pretrained MoE bases after one shared three-stage SFT (chat, thinking, terminal agent), used as comparable starting points for post-training research.
Note Snowball 67B-A2B (Grug MoE)
open-athena/Nemotron-3-Nano-30B-A3B-Chat-Aligned-Base-2026.10.30
Text Generation • 32B • Updated • 637Note Nemotron-3-Nano 30B-A3B (NemotronH)
open-athena/Qwen3-30B-A3B-Chat-Aligned-Base-2026.10.30
Text Generation • 31B • Updated • 591Note Qwen3 30B-A3B (Qwen3-MoE), native chat template
open-athena/Qwen3.5-35B-A3B-Chat-Aligned-Base-2026.10.31
Text Generation • 35B • Updated • 967Note Qwen3.5 35B-A3B (Qwen3.5-MoE), native chat template