LLM EXPLORER 61,561 MODELS INDEXED

Meta Llama 3 8B Instruct 8bit by pkalbhor

By pkalbhor · 8 downloads
HF Repo ↗ Copy URL

Meta Llama 3 8B Instruct 8bit is an open-source language model by pkalbhor. Features: 8b LLM, VRAM: 9.1GB, Context: 8K, Quantized, Instruction-Based, LLM Explorer Score: 0.14, Arc: 59.6, HellaSwag: 78.8, MMLU: 65.1, GSM8K: 57.3.

  Arxiv:1910.09700   8-bit   8bit   Autotrain compatible   Bitsandbytes   Endpoints compatible   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/pkalbhor/Meta-Llama-3-8B-Instruct-8bit 

Meta Llama 3 8B Instruct 8bit Parameters and Internals

LLM NameMeta Llama 3 8B Instruct 8bit
Repository 🤗https://huggingface.co/pkalbhor/Meta-Llama-3-8B-Instruct-8bit 
Base Model(s)  ...eta Llama 3 8B Instruct FP8 KV   neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV
Model Size8b
Required VRAM9.1 GB
Updated2025-09-23
Maintainerpkalbhor
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Quantization Type8bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.42.0.dev0
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Meta Llama 3 8B Instruct 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB102
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB111
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB22
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB50
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB52525
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB21317
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB23
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB51
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB111
...B Instruct 262k V2 EXL2 5.0bpw256K / 5.8 GB51