4-bit 4bit Autotrain compatible Axolotl Base model:nousresearch/deephe... Base model:quantized:nousresea... Chat Chatml Conversational Distillation En Endpoints compatible Finetuned Function calling Gpt4 Instruct Json mode Llama Llama-3 Mlx Quantized R1 Reasoning Region:us Roleplaying Safetensors Synthetic data Vllm
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepHermes-3-Llama-3-8B-Preview-4Bit
DeepHermes 3 Llama 3 8B Preview 4Bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
DeepHermes 3 Llama 3 8B Preview 4Bit Parameters and Internals
| LLM Name | DeepHermes 3 Llama 3 8B Preview 4Bit |
| Repository 🤗 | https://huggingface.co/mlx-community/DeepHermes-3-Llama-3-8B-Preview-4Bit |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 4.5 GB |
| Updated | 2025-08-17 |
| Maintainer | mlx-community |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | llama3 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to DeepHermes 3 Llama 3 8B Preview 4Bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...B Instruct Gradient 1048K 4bit | 1024K / 4.5 GB | 10 | 2 |
| ...B Instruct Gradient 1048K 8bit | 1024K / 8.6 GB | 5 | 1 |
| ...truct Gradient 1048K Bpw6 EXL2 | 1024K / 6.7 GB | 3 | 2 |
| ...truct Gradient 1048K Bpw5 EXL2 | 1024K / 5.8 GB | 5 | 0 |
| Llama 3 8B Instruct 1048K 4bit | 1024K / 4.5 GB | 258 | 25 |
| Llama 3 8B Instruct 1048K 8bit | 1024K / 8.6 GB | 181 | 17 |
| ... Gradient 1048K 8.0bpw H8 EXL2 | 1024K / 8.6 GB | 3 | 3 |
| ...ct Gradient 1048K Bpw2.25 EXL2 | 1024K / 3.4 GB | 3 | 1 |
| Llama 3 8B Instruct 262K 2bit | 256K / 2.5 GB | 9 | 1 |
| ...B Instruct 262k V2 EXL2 6.0bpw | 256K / 6.7 GB | 6 | 1 |
Rank the DeepHermes 3 Llama 3 8B Preview 4Bit Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 50728 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124