LLM EXPLORER 59,420 MODELS INDEXED

Llama 3 SauerkrautLM 8B Instruct EXL2 by mayflowergmbh

By mayflowergmbh · 5 downloads

Llama 3 SauerkrautLM 8B Instruct EXL2 is an open-source language model by mayflowergmbh. Features: 8b LLM, VRAM: 5.8GB, Context: 8K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.13, Arc: 73.7, HellaSwag: 89.4, MMLU: 68.1, GSM8K: 65.

  5-bit   Conversational   De   Dpo   En   Endpoints compatible   Exl2   Instruct   Llama   Quantized   Region:us   Safetensors   Two stage dpo

Llama 3 SauerkrautLM 8B Instruct EXL2 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Business applications
Primary Use Cases:
Language understanding and generation
Additional Notes 
Due to inherent limitations, possibly uncensored content cannot be completely ruled out. Licensing does not constitute legal advice.
Supported Languages 
German (Proficient), English (Proficient)
Training Details 
Data Sources:
German curated data
Data Volume:
70k for first epoch and 20k for second epoch
Methodology:
Two-stage DPO Fine-Tuning
Input Output 
Input Format:
<|begin_of_text|><|start_header_id|>system<|end_header_id|> user<|eot_id|><|start_header_id|>user<|end_header_id|> Input<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Accepted Modalities:
Text
LLM NameLlama 3 SauerkrautLM 8B Instruct EXL2
Repository πŸ€—https://huggingface.co/mayflowergmbh/Llama-3-SauerkrautLM-8b-Instruct-EXL2 
Base Model(s)  ...ama 3 SauerkrautLM 8B Instruct   VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
Model Size8b
Required VRAM5.8 GB
Updated2026-06-07
Maintainermayflowergmbh
Model Typellama
Instruction-BasedYes
Model Files  5.8 GB
Supported Languagesde en
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 SauerkrautLM 8B Instruct 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 mayflowergmbh/Llama-3-SauerkrautLM-8b-Instruct-EXL2.