LLM EXPLORER 61,491 MODELS INDEXED

Daredevil 8B Abliterated AWQ by aspirina765

By aspirina765 · 6 downloads
HF Repo ↗ Copy URL

Daredevil 8B Abliterated AWQ is an open-source language model by aspirina765. Features: 8b LLM, VRAM: 5.8GB, Context: 8K, Quantized, LLM Explorer Score: 0.13.

  Arxiv:1910.09700   4-bit   Autoquant   Autotrain compatible   Awq   Conversational   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/aspirina765/Daredevil-8B-abliterated-AWQ 

Daredevil 8B Abliterated AWQ Parameters and Internals

LLM NameDaredevil 8B Abliterated AWQ
Repository 🤗https://huggingface.co/aspirina765/Daredevil-8B-abliterated-AWQ 
Base Model(s)  Daredevil 8B Abliterated   mlabonne/Daredevil-8B-abliterated
Model Size8b
Required VRAM5.8 GB
Updated2025-09-23
Maintaineraspirina765
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Daredevil 8B Abliterated AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB80
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB71
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB54
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB60
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB90
Llama 3 8B Instruct AWQ8K / 5.8 GB2545831
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB60
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB5630
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB70
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB4015
Note: green Score (e.g. "73.2") means that the model is better than aspirina765/Daredevil-8B-abliterated-AWQ.