LLM EXPLORER 58,873 MODELS INDEXED

Model 3 by Sakalti

By Sakalti · 14 downloads
HF Repo ↗ Copy URL

Model 3 is an open-source language model by Sakalti. Features: 7b LLM, VRAM: 15.2GB, Context: 128K, Instruction-Based, Merged, LLM Explorer Score: 0.25.

  Merged Model   Arxiv:2306.01708   Base model:qwen/qwen2.5-7b Base model:qwen/qwen2.5-7b-ins...   Conversational   Endpoints compatible   Instruct   Model-index   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/model-3 

Model 3 Parameters and Internals

LLM NameModel 3
Repository 🤗https://huggingface.co/Sakalti/model-3 
Base Model(s)  Qwen/Qwen2.5-7B   Qwen/Qwen2.5-7B-Instruct   Qwen/Qwen2.5-7B   Qwen/Qwen2.5-7B-Instruct
Merged ModelYes
Model Size7b
Required VRAM15.2 GB
Updated2026-08-07
MaintainerSakalti
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   0.3 GB: 4-of-4
Model ArchitectureQwen2ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.46.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Model 3

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB52534373
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB102
Qwen2.5 7B RRP 1M986K / 15.2 GB56
Qwen2.5 7B CelestialHarmony 1M986K / 14.8 GB87
Q2.5 Instruct 1M Harmony986K / 15.2 GB42
Impish QWEN 7B 1M986K / 15.2 GB46
COCO 7B Instruct 1M986K / 15.2 GB94
Apollo 7B986K / 15.2 GB80
Graph R1 7B986K / 15.3 GB73
Qwen2.5 7B Sky R1 Mini986K / 15.2 GB60
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/model-3.