LLM EXPLORER 67,181 MODELS INDEXED

Tantrum 16bit by dbands

By dbands · 15 downloads
HF Repo ↗ Copy URL

Tantrum 16bit is an open-source language model by dbands. Features: 7b LLM, VRAM: 15.2GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

  16bit Base model:dphn/dolphin-2.9.2-... Base model:finetune:dphn/dolph...   Conversational Dataset:dbands/scoredpythonins...   En   Endpoints compatible   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/dbands/tantrum_16bit 

Tantrum 16bit Parameters and Internals

LLM NameTantrum 16bit
Repository 🤗https://huggingface.co/dbands/tantrum_16bit 
Base Model(s)  cognitivecomputations/dolphin-2.9.2-qwen2-7b   cognitivecomputations/dolphin-2.9.2-qwen2-7b
Model Size7b
Required VRAM15.2 GB
Updated2026-08-04
Maintainerdbands
Model Typeqwen2
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4
Supported Languagesen
Quantization Type16bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.43.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Tantrum 16bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB44411
...wen2.5 7B Instruct 1M Bnb 4bit986K / 5.5 GB2671
Qwen2.5 7B Instruct 1M 8bit986K / 8.1 GB634
Qwen2.5 7B Instruct 1M 6bit986K / 6.2 GB522
...B Instruct 1M Unsloth Bnb 4bit986K / 7.5 GB373
Qwen 7B Kiberbase128K / 15.2 GB7880
A1 V002128K / 15.2 GB70
Mini Pathfinder128K / 15.2 GB160
A1 V0.0.1128K / 15.2 GB80
CogitoDistil128K / 15.2 GB140
Note: green Score (e.g. "73.2") means that the model is better than dbands/tantrum_16bit.