LLM EXPLORER 64,069 MODELS INDEXED

Torchcast Decision 27B by torchcast-ai

By torchcast-ai · 1068 downloads
HF Repo ↗ Copy URL

Torchcast Decision 27B is an open-source language model by torchcast-ai. Features: 27b LLM, VRAM: 54.7GB, License: cc-by-nc-4.0, LLM Explorer Score: 0.34.

  Conversational   Decision-index   Decision-model   En   Endpoints compatible   Image-text-to-text   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Typed-decisions
Model Card on HF 🤗: https://huggingface.co/torchcast-ai/torchcast-decision-27b 

Torchcast Decision 27B Parameters and Internals

LLM NameTorchcast Decision 27B
Repository 🤗https://huggingface.co/torchcast-ai/torchcast-decision-27b 
Model Size27b
Required VRAM54.7 GB
Updated2026-10-13
Maintainertorchcast-ai
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-12   4.8 GB: 2-of-12   5.0 GB: 3-of-12   4.9 GB: 4-of-12   5.0 GB: 5-of-12   4.9 GB: 6-of-12   5.0 GB: 7-of-12   4.9 GB: 8-of-12   5.0 GB: 9-of-12   5.0 GB: 10-of-12   4.9 GB: 11-of-12   2.8 GB: 12-of-12
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licensecc-by-nc-4.0
Model Max Length262144
Transformers Version5.8.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Torchcast Decision 27B

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 torchcast-ai/torchcast-decision-27b.