LLM EXPLORER 63,407 MODELS INDEXED

GRM 2.6 Plus 0628 by OrionLLM

By OrionLLM · 1430 downloads
HF Repo ↗ Copy URL

GRM 2.6 Plus 0628 is an open-source language model by OrionLLM. Features: 27b LLM, VRAM: 55.4GB, License: apache-2.0, LLM Explorer Score: 0.29.

Base model:finetune:orionllm/g... Base model:orionllm/grm-2.6-pl...   Conversational   Eval-results   Image-text-to-text   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/OrionLLM/GRM-2.6-Plus-0628 

GRM 2.6 Plus 0628 Parameters and Internals

LLM NameGRM 2.6 Plus 0628
Repository 🤗https://huggingface.co/OrionLLM/GRM-2.6-Plus-0628 
Model NameQwen/Qwen3.6-27B
Base Model(s)  OrionLLM/GRM-2.6-Plus   OrionLLM/GRM-2.6-Plus
Model Size27b
Required VRAM55.4 GB
Updated2026-08-05
MaintainerOrionLLM
Model Typeqwen3_5
Model Files  4.0 GB: 1-of-15   3.9 GB: 2-of-15   3.9 GB: 3-of-15   3.9 GB: 4-of-15   3.9 GB: 5-of-15   3.9 GB: 6-of-15   4.0 GB: 7-of-15   3.9 GB: 8-of-15   3.9 GB: 9-of-15   3.9 GB: 10-of-15   3.9 GB: 11-of-15   3.9 GB: 12-of-15   4.0 GB: 13-of-15   3.9 GB: 14-of-15   0.5 GB: 15-of-15
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to GRM 2.6 Plus 0628

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB873
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB95131835
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B FP80K / 0.4 GB123157416
Note: green Score (e.g. "73.2") means that the model is better than OrionLLM/GRM-2.6-Plus-0628.