LLM EXPLORER 64,069 MODELS INDEXED

Jebadiah 27B V2.1 by frontier-infra

By frontier-infra · 12 downloads
HF Repo ↗ Copy URL

Jebadiah 27B V2.1 is an open-source language model by frontier-infra. Features: 27b LLM, VRAM: 55.6GB, License: apache-2.0, Merged, LLM Explorer Score: 0.27.

  Merged Model Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.8-27b   Calibrated-probabilities   Conversational   Decision-model   En   Endpoints compatible   Image-text-to-text   Lora   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Typed-decisions
Model Card on HF 🤗: https://huggingface.co/frontier-infra/jebadiah-27b-v2-1 

Jebadiah 27B V2.1 Parameters and Internals

LLM NameJebadiah 27B V2.1
Repository 🤗https://huggingface.co/frontier-infra/jebadiah-27b-v2-1 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Merged ModelYes
Model Size27b
Required VRAM55.6 GB
Updated2026-10-13
Maintainerfrontier-infra
Model Typeqwen3_5
Model Files  4.0 GB: 1-of-18   3.0 GB: 2-of-18   2.5 GB: 3-of-18   4.0 GB: 4-of-18   2.1 GB: 5-of-18   4.0 GB: 6-of-18   2.1 GB: 7-of-18   4.0 GB: 8-of-18   2.1 GB: 9-of-18   4.0 GB: 10-of-18   2.1 GB: 11-of-18   4.0 GB: 12-of-18   2.1 GB: 13-of-18   4.0 GB: 14-of-18   2.1 GB: 15-of-18   4.0 GB: 16-of-18   2.1 GB: 17-of-18   3.4 GB: 18-of-18
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
LoRA ModelYes
Errorsreplace

Best Alternatives to Jebadiah 27B V2.1

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB823
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB150642103
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 frontier-infra/jebadiah-27b-v2-1.