LLM EXPLORER 59,516 MODELS INDEXED

Llama 3 8B Irene V0.2 6.5bpw H8 EXL2 by Meggido

By Meggido · 6 downloads
HF Repo ↗ Copy URL

Llama 3 8B Irene V0.2 6.5bpw H8 EXL2 is an open-source language model by Meggido. Features: 8b LLM, VRAM: 7.2GB, Context: 8K, License: other, Quantized, Merged, LLM Explorer Score: 0.12.

  Merged Model Base model:finetune:grimjim/ll... Base model:grimjim/llama-3-mer...   Conversational   Endpoints compatible   Exl2   Facebook   Llama   Llama-3   Meta   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Meggido/Llama-3-8B-Irene-v0.2-6.5bpw-h8-exl2 

Llama 3 8B Irene V0.2 6.5bpw H8 EXL2 Parameters and Internals

Model Type 
text-generation
LLM NameLlama 3 8B Irene V0.2 6.5bpw H8 EXL2
Repository 🤗https://huggingface.co/Meggido/Llama-3-8B-Irene-v0.2-6.5bpw-h8-exl2 
Base Model(s)  Llama 3 Merge Virt Req 8B   grimjim/llama-3-merge-virt-req-8B
Merged ModelYes
Model Size8b
Required VRAM7.2 GB
Updated2026-08-06
MaintainerMeggido
Model Typellama
Model Files  7.2 GB
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 8B Irene V0.2 6.5bpw H8 EXL2

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
Note: green Score (e.g. "73.2") means that the model is better than Meggido/Llama-3-8B-Irene-v0.2-6.5bpw-h8-exl2.