LLM EXPLORER 59,358 MODELS INDEXED

Qwen2 1.5B MAC Gguf Q8 0 by inflaton

By inflaton · 23 downloads
HF Repo ↗ Copy URL

Qwen2 1.5B MAC Gguf Q8 0 is an open-source language model by inflaton. Features: 1.5b LLM, VRAM: 0.4GB, License: apache-2.0, Quantized, Merged, LLM Explorer Score: 0.13.

  Merged Model   4bit Base model:inflaton/qwen2-1.5b... Base model:quantized:inflaton/...   En   Endpoints compatible   Gguf   Q8   Q8 0   Quantized   Qwen2   Region:us   Unsloth
Model Card on HF 🤗: https://huggingface.co/inflaton/Qwen2-1.5B-MAC-gguf-q8_0 

Qwen2 1.5B MAC Gguf Q8 0 Parameters and Internals

Model Type 
text-generation-inference, transformers
Additional Notes 
This model was trained using Unsloth for faster training times.
Training Details 
Methodology:
Finetuned using Unsloth and Huggingface's TRL library
Training Time:
2x faster than traditional methods
LLM NameQwen2 1.5B MAC Gguf Q8 0
Repository 🤗https://huggingface.co/inflaton/Qwen2-1.5B-MAC-gguf-q8_0 
Base Model(s)  inflaton/Qwen2-1.5B-merged_4bit_forced   inflaton/Qwen2-1.5B-merged_4bit_forced
Merged ModelYes
Model Size1.5b
Required VRAM0.4 GB
Updated2024-11-11
Maintainerinflaton
Model Typeqwen2
Model Files  0.4 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|q8|q8_0|4bit
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Qwen2 1.5B MAC Gguf Q8 0

Best Alternatives
Context / RAM
Downloads
Likes
MoeinGTS1.5 1.5B0K / 1 GB1131
MedScholar 1.5B F32 GGUF0K / 0.7 GB843
Qwen2 1.5B Instruct GGUF0K / 0.4 GB3468
Jenna V3 Qwen2 1.5 GGUF Q40K / 1 GB290
Jenna V3 Qwen2 1.5 GGUF0K / 3.1 GB241
Qwen2 1.5B Ita V20K / 0.1 GB160
Qwen2 1.5B0K / 1.1 GB130
Qwen2 1.5B MAC Gguf Q4 K M0K / 0.3 GB220
Qwen2 1.5B MAC Gguf F160K / 3.1 GB170
Qwen2 1.5B Gguf F160K / 3.1 GB160
Note: green Score (e.g. "73.2") means that the model is better than inflaton/Qwen2-1.5B-MAC-gguf-q8_0.