LLM EXPLORER 57,918 MODELS INDEXED

Umbr0x 1.5B V3.1 16bit by gabrielbosse9

By gabrielbosse9 · 10 downloads
HF Repo ↗ Copy URL

Umbr0x 1.5B V3.1 16bit is an open-source language model by gabrielbosse9. Features: 7b LLM, VRAM: 15.2GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.18.

  4bit   Autotrain compatible   En   Endpoints compatible   Pytorch   Quantized   Qwen2   Region:us   Sft   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/gabrielbosse9/Umbr0x-1.5B-V3.1-16bit 

Umbr0x 1.5B V3.1 16bit Parameters and Internals

LLM NameUmbr0x 1.5B V3.1 16bit
Repository 🤗https://huggingface.co/gabrielbosse9/Umbr0x-1.5B-V3.1-16bit 
Base Model(s)  unsloth/qwen2.5-7b-unsloth-bnb-4bit   unsloth/qwen2.5-7b-unsloth-bnb-4bit
Model Size7b
Required VRAM15.2 GB
Updated2025-04-27
Maintainergabrielbosse9
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 Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Quantized Models of the Umbr0x 1.5B V3.1 16bit

Model
Likes
Downloads
VRAM
Umbr0x 1.5B V3.1 16bit 201915 GB

Best Alternatives to Umbr0x 1.5B V3.1 16bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB44411
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
Legal Qwen2.5 7B Sft128K / 15.2 GB6680
A1 V002128K / 15.2 GB70
Mini Pathfinder128K / 15.2 GB160
A1 V0.0.1128K / 15.2 GB80
CogitoDistil128K / 15.2 GB140
Alisia 7B Instruct V1128K / 15.4 GB1142
Note: green Score (e.g. "73.2") means that the model is better than gabrielbosse9/Umbr0x-1.5B-V3.1-16bit.