LLM EXPLORER 62,323 MODELS INDEXED

Grug 67B A2B GLM53 RLVR SFT 2026.09.23 by open-athena

By open-athena · 191 downloads

Grug 67B A2B GLM53 RLVR SFT 2026.09.23 is an open-source language model by open-athena. Features: 67b LLM, VRAM: 146.8GB, Context: 256K, License: openmdw-1.1, LLM Explorer Score: 0.3.

Base model:finetune:open-athen... Base model:open-athena/grug-67...   Conversational   Finetuned   Grug moe   Region:us   Safetensors   Sharded   Tensorflow

Grug 67B A2B GLM53 RLVR SFT 2026.09.23 Parameters and Internals

LLM NameGrug 67B A2B GLM53 RLVR SFT 2026.09.23
Repository πŸ€—https://huggingface.co/open-athena/Grug-67B-A2B-GLM53-RLVR-SFT-2026.09.23 
Base Model(s)  open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.21   open-athena/Grug-67B-A2B-Datakit-SFT-262K-2026.09.21
Model Size67b
Required VRAM146.8 GB
Updated2026-09-27
Maintaineropen-athena
Model Typegrug_moe
Model Files  2.6 GB: 1-of-79   3.4 GB: 2-of-79   3.4 GB: 3-of-79   3.5 GB: 4-of-79   3.4 GB: 5-of-79   3.4 GB: 6-of-79   3.5 GB: 7-of-79   3.4 GB: 8-of-79   3.4 GB: 9-of-79   3.5 GB: 10-of-79   3.4 GB: 11-of-79   3.4 GB: 12-of-79   3.5 GB: 13-of-79   3.4 GB: 14-of-79   3.4 GB: 15-of-79   3.5 GB: 16-of-79   3.4 GB: 17-of-79   3.4 GB: 18-of-79   3.5 GB: 19-of-79   3.4 GB: 20-of-79   3.4 GB: 21-of-79   3.5 GB: 22-of-79   3.4 GB: 23-of-79   3.4 GB: 24-of-79   3.5 GB: 25-of-79   3.4 GB: 26-of-79   3.4 GB: 27-of-79   3.5 GB: 28-of-79   3.4 GB: 29-of-79   3.4 GB: 30-of-79   3.5 GB: 31-of-79   3.4 GB: 32-of-79   3.4 GB: 33-of-79   3.5 GB: 34-of-79   3.4 GB: 35-of-79   3.4 GB: 36-of-79   3.5 GB: 37-of-79   3.4 GB: 38-of-79   3.4 GB: 39-of-79   3.5 GB: 40-of-79   3.4 GB: 41-of-79   3.4 GB: 42-of-79   3.5 GB: 43-of-79
Model ArchitectureGrugMoeForCausalLM
Licenseopenmdw-1.1
Context Length262144
Model Max Length262144
Transformers Version5.12.1
Vocabulary Size128256

Best Alternatives to Grug 67B A2B GLM53 RLVR SFT 2026.09.23

Best Alternatives
Context / RAM
Downloads
Likes
...2B Datakit SFT 262K 2026.09.21256K / 133.9 GB4670
...2B Datakit SFT 262K 2026.09.11256K / 70.6 GB3391
...7B A2b Sft S2 Thinking Step63064K / 133.9 GB3500
...7B A2b Sft S1 Wildchat Step25764K / 133.9 GB2330
Note: green Score (e.g. "73.2") means that the model is better than open-athena/Grug-67B-A2B-GLM53-RLVR-SFT-2026.09.23.