LLM EXPLORER 59,420 MODELS INDEXED

Llama3.1 Merged by anthonymeo

By anthonymeo · 6 downloads
HF Repo ↗ Copy URL

Llama3.1 Merged is an open-source language model by anthonymeo. Features: 8.2b LLM, VRAM: 5.8GB, Context: 128K, Quantized, Merged, LLM Explorer Score: 0.14.

  Merged Model   Arxiv:1910.09700   4-bit   4bit   Bitsandbytes   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/anthonymeo/llama3.1-merged 

Llama3.1 Merged Parameters and Internals

LLM NameLlama3.1 Merged
Repository 🤗https://huggingface.co/anthonymeo/llama3.1-merged 
Merged ModelYes
Model Size8.2b
Required VRAM5.8 GB
Updated2026-08-08
Maintaineranthonymeo
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama3.1 Merged

Best Alternatives
Context / RAM
Downloads
Likes
KernelLLM Bnb 4bit128K / 5.7 GB91
KernelLLM Unsloth Bnb 4bit128K / 6 GB62
EPFL TA Meister 4bit8K / 5.8 GB60
Book 4bitV58K / 5.8 GB60
Book 4bit8K / 5.8 GB60
Llama3 Ko 4bit8K / 5.8 GB50
Ko Pt Model Test18K / 16.4 GB20270
Maqa Llama 4bit8K / 5.8 GB90
Hola8K / 5.8 GB60
Llama SciQ 4bits8K / 5.8 GB120
Note: green Score (e.g. "73.2") means that the model is better than anthonymeo/llama3.1-merged.