LLM EXPLORER 60,783 MODELS INDEXED

Meta Llama 3.1 70B Instruct Gptq 4bit by ModelCloud

By ModelCloud · 7 downloads
HF Repo ↗ Copy URL

Meta Llama 3.1 70B Instruct Gptq 4bit is an open-source language model by ModelCloud. Features: 70b LLM, VRAM: 39.9GB, Context: 128K, License: meta, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  4-bit   4bit   70b   Conversational   Endpoints compatible   Gptq   Gptqmodel   Instruct   Int4   Llama   Llama-3.1   Modelcloud   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit 

Meta Llama 3.1 70B Instruct Gptq 4bit Parameters and Internals

LLM NameMeta Llama 3.1 70B Instruct Gptq 4bit
Repository 🤗https://huggingface.co/ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit 
Model Size70b
Required VRAM39.9 GB
Updated2026-07-26
MaintainerModelCloud
Model Typellama
Instruction-BasedYes
Model Files  8.0 GB: 1-of-5   8.0 GB: 2-of-5   8.0 GB: 3-of-5   8.0 GB: 4-of-5   7.9 GB: 5-of-5
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licensemeta
Context Length131072
Model Max Length131072
Transformers Version4.44.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Meta Llama 3.1 70B Instruct Gptq 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB5176
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB1290
...ta Llama 3 70B Instruct Marlin8K / 39.5 GB1416
...ama 3 Taiwan 70B Instruct GPTQ8K / 39.8 GB62
Meta Llama 3 70B Instruct GPTQ8K / 39.8 GB90516
Meta Llama 3 70B Instruct GPTQ8K / 39.8 GB76319
...g Llama 3 70B Instruct GPTQ 4B8K / 39.8 GB60
...g Llama 3 70B Instruct GPTQ 8B8K / 74.4 GB31
...a Llama 3 70B Instruct GPTQ 8B8K / 74.4 GB170
...erkrautLM 70B Instruct GPTQ 8B8K / 74.4 GB41
Note: green Score (e.g. "73.2") means that the model is better than ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit.