LLM EXPLORER 61,491 MODELS INDEXED

Hermes 2 Pro Llama 3 8B by NousResearch

By NousResearch · 4240 downloads
HF Repo ↗ Copy URL

Hermes 2 Pro Llama 3 8B is an open-source language model by NousResearch. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: llama3, LLM Explorer Score: 0.24, Arc: 63.5, HellaSwag: 83.2, MMLU: 64.8, GSM8K: 67.9.

  Axolotl Base model:finetune:nousresear... Base model:nousresearch/meta-l...   Chatml   Conversational   Dataset:teknium/openhermes-2.5   Deploy:azure   Deploy:sagemaker   Distillation   Dpo   En   Endpoints compatible   Finetuned   Function calling   Gpt4   Instruct   Json mode   Llama   Llama-3   Region:us   Rlhf   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B 

Hermes 2 Pro Llama 3 8B Parameters and Internals

Model Type 
instruct, finetune, chatml, DPO, RLHF, gpt4, synthetic data, distillation, function calling, json mode
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
general task, conversation, Function Calling, JSON Structured Outputs
Additional Notes 
Supports special Multi-turn Function Calling structure with a new ChatML role.
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
teknium/OpenHermes-2.5
Methodology:
Updated, retrained version with cleaned and new datasets including Function Calling and JSON Mode dataset.
Input Output 
Input Format:
ChatML
Accepted Modalities:
text
Output Format:
JSON, structured outputs
Performance Tips:
Use 'add_generation_prompt=True' when calling 'apply_chat_template()'
LLM NameHermes 2 Pro Llama 3 8B
Repository 🤗https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B 
Base Model(s)  Meta Llama 3 8B   NousResearch/Meta-Llama-3-8B
Model Size8b
Required VRAM16.1 GB
Updated2026-08-05
MaintainerNousResearch
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128288
Torch Data Typefloat16

Quantized Models of the Hermes 2 Pro Llama 3 8B

Model
Likes
Downloads
VRAM
Hermes 2 Pro Llama 3 8B AWQ112485 GB
Hermes 2 Theta Llama 3 8B 4bit194 GB
Hermes 2 Theta Llama 3 8B 8bit168 GB
Hermes 2 Pro Llama 3 8B GGUF23543 GB
...2 Theta Llama 3 8B 4 0bpw EXL2065 GB
...2 Theta Llama 3 8B 2 2bpw EXL2063 GB
...2 Theta Llama 3 8B 6 5bpw EXL2057 GB
... Theta Llama 3 8B EXL2 4.75bpw085 GB
...Llama3 Entity Mapping Gguf F1602116 GB
...ro Llama 3 8B Bnb 4bit Smashed0156 GB

Best Alternatives to Hermes 2 Pro Llama 3 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1135125
UltraLong Thinking4192K / 16.1 GB23
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB12418
Cthulhu 8B V1.41048K / 16.1 GB1010
...raLong 1M Instruct Abliterated1048K / 32.1 GB49
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB70259
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB254