LLM EXPLORER 60,783 MODELS INDEXED

Smaug Llama 3 70B Instruct GPTQ 4B by cortecs

By cortecs · 6 downloads
HF Repo ↗ Copy URL

Smaug Llama 3 70B Instruct GPTQ 4B is an open-source language model by cortecs. Features: 70b LLM, VRAM: 39.8GB, Context: 8K, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

  Arxiv:1910.09700   4-bit   4bit   Autotrain compatible   Conversational   Endpoints compatible   Gptq   Instruct   Llama   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cortecs/Smaug-Llama-3-70B-Instruct-GPTQ-4b 

Smaug Llama 3 70B Instruct GPTQ 4B Parameters and Internals

LLM NameSmaug Llama 3 70B Instruct GPTQ 4B
Repository 🤗https://huggingface.co/cortecs/Smaug-Llama-3-70B-Instruct-GPTQ-4b 
Base Model(s)  Smaug Llama 3 70B Instruct   abacusai/Smaug-Llama-3-70B-Instruct
Model Size70b
Required VRAM39.8 GB
Updated2025-09-24
Maintainercortecs
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
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Smaug Llama 3 70B Instruct GPTQ 4B

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 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 cortecs/Smaug-Llama-3-70B-Instruct-GPTQ-4b.