LLM EXPLORER 60,783 MODELS INDEXED

Meta Llama 3 70B Instruct GPTQ Int4 by study-hjt

By study-hjt · 19 downloads
HF Repo ↗ Copy URL

Meta Llama 3 70B Instruct GPTQ Int4 is an open-source language model by study-hjt. Features: 70b LLM, VRAM: 39.8GB, Context: 8K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

  4-bit   En   Endpoints compatible   Facebook   Gptq   Instruct   Int4   Llama   Llama-3   Llama3   Meta   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/study-hjt/Meta-Llama-3-70B-Instruct-GPTQ-Int4 

Meta Llama 3 70B Instruct GPTQ Int4 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Commercial, Research
Applications:
Assistant-like chat, Natural language generation
Primary Use Cases:
English language generation tasks
Limitations:
Use in languages other than English without proper fine-tuning, Use that violates applicable laws
Considerations:
Considerations for tailored safety testing for specific applications
Additional Notes 
Llama 3 supports only English language generation outright. Developers may fine-tune it to support additional languages.
Training Details 
Data Sources:
Publicly available online data
Data Volume:
15 trillion tokens
Methodology:
Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Context Length:
8000
Hardware Used:
Meta's Research SuperCluster, H100-80GB GPUs
Model Architecture:
Auto-regressive language model, optimized transformer architecture
Safety Evaluation 
Methodologies:
Red teaming, Adversarial evaluations
Findings:
Reduction of residual risks, Model refusal mitigation
Risk Categories:
CBRNE, Cybersecurity, Child Safety
Ethical Considerations:
Ethical guidelines for responsible AI deployment outlined
Responsible Ai Considerations 
Transparency:
An open approach to AI for better product safety and innovation
Mitigation Strategies:
Updated Responsible Use Guide, Meta Llama Guard 2, Code Shield
Input Output 
Input Format:
Text
Accepted Modalities:
Text
Output Format:
Text and code generation
LLM NameMeta Llama 3 70B Instruct GPTQ Int4
Repository 🤗https://huggingface.co/study-hjt/Meta-Llama-3-70B-Instruct-GPTQ-Int4 
Base Model(s)  ...a Llama 3 70B Instruct Ov Int4   fakezeta/Meta-Llama-3-70B-Instruct-ov-int4
Model Size70b
Required VRAM39.8 GB
Updated2026-08-06
Maintainerstudy-hjt
Model Typellama
Instruction-BasedYes
Model Files  10.0 GB: 1-of-4   10.0 GB: 2-of-4   9.9 GB: 3-of-4   9.9 GB: 4-of-4
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Meta Llama 3 70B Instruct GPTQ Int4

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB5176
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB1290
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB74
...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
Note: green Score (e.g. "73.2") means that the model is better than study-hjt/Meta-Llama-3-70B-Instruct-GPTQ-Int4.