LLM EXPLORER 59,420 MODELS INDEXED

Llama 3.3 70B Instruct HIGGS 4bit by ISTA-DASLab

By ISTA-DASLab · 5 downloads
HF Repo ↗ Copy URL

Llama 3.3 70B Instruct HIGGS 4bit is an open-source language model by ISTA-DASLab. Features: 70b LLM, VRAM: 39GB, Context: 128K, Quantized, Instruction-Based, LLM Explorer Score: 0.15.

  Arxiv:1910.09700   4-bit   4bit   Conversational   Endpoints compatible   Higgs   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/Llama-3.3-70B-Instruct-HIGGS-4bit 

Llama 3.3 70B Instruct HIGGS 4bit Parameters and Internals

LLM NameLlama 3.3 70B Instruct HIGGS 4bit
Repository 🤗https://huggingface.co/ISTA-DASLab/Llama-3.3-70B-Instruct-HIGGS-4bit 
Model Size70b
Required VRAM39 GB
Updated2026-07-18
MaintainerISTA-DASLab
Model Typellama
Instruction-BasedYes
Model Files  4.9 GB: 1-of-8   4.9 GB: 2-of-8   5.0 GB: 3-of-8   4.9 GB: 4-of-8   4.9 GB: 5-of-8   5.0 GB: 6-of-8   4.9 GB: 7-of-8   4.5 GB: 8-of-8
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.47.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3.3 70B Instruct HIGGS 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB415
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB253
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB252
...0B Instruct Gradient 262K 4bit256K / 39.7 GB253
...0B Instruct Gradient 262K 8bit256K / 75 GB262
...0B Instruct Gradient 262K 2bit256K / 21.9 GB201
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB71
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB60
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60