LLM EXPLORER 61,491 MODELS INDEXED

Llama 3 8B Instruct 262K 4bit GPTQ by Ksgk-fy

By Ksgk-fy · 5 downloads
HF Repo ↗ Copy URL

Llama 3 8B Instruct 262K 4bit GPTQ is an open-source language model by Ksgk-fy. Features: 8b LLM, VRAM: 5.8GB, Context: 256K, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

  4-bit   4bit   Conversational   Endpoints compatible   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Ksgk-fy/Llama-3-8B-Instruct-262k-4bit-GPTQ 

Llama 3 8B Instruct 262K 4bit GPTQ Parameters and Internals

Model Type 
text generation, instruct
Additional Notes 
Quantized to be compatible with vLLM inference.
LLM NameLlama 3 8B Instruct 262K 4bit GPTQ
Repository 🤗https://huggingface.co/Ksgk-fy/Llama-3-8B-Instruct-262k-4bit-GPTQ 
Model Size8b
Required VRAM5.8 GB
Updated2026-08-06
MaintainerKsgk-fy
Model Typellama
Instruction-BasedYes
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Context Length262144
Model Max Length262144
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3 8B Instruct 262K 4bit GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
... 8B Instruct 262K 4bit GPTQ 02256K / 5.7 GB60
...Instruct V0.5 GPTQ Safetensors128K / 4.9 GB1130
...lama 3.1 8B Instruct GPTQ INT4128K / 5.8 GB916942
...Instruct 80K Qlora Merged GPTQ80K / 5.8 GB60
...oLeo Instruct 8B 32K V0.1 GPTQ64K / 5.7 GB50
Meta Llama 3 8B Instruct GPTQ8K / 5.8 GB60
...ta Llama 3 8B Instruct GPTQ 8B8K / 9.2 GB70
Meta Llama 3 8B Instruct GPTQ8K / 5.8 GB71
...truct Abliterated V3 GPTQ 4bit8K / 5.8 GB90
Meta Llama 3 8B Instruct GPTQ8K / 5.7 GB28957
Note: green Score (e.g. "73.2") means that the model is better than Ksgk-fy/Llama-3-8B-Instruct-262k-4bit-GPTQ.