DeepHermes-3-Llama-3-8B-Preview GGUF Quantized Models
Technical Details
- Quantization Tool: llama.cpp
- Version: version: 5097 (fe5b78c8)
Model Information
- Base Model: NousResearch/DeepHermes-3-Llama-3-8B-Preview
- Quantized by: matrixportal
Available Files
| 🚀 Download | 🔢 Type | 📦 Size | 📝 Description |
|---|---|---|---|
| Download | Q3 K M | 4.02GB | Small, acceptable quality |
| Download | Q4 0 | 4.66B | Standard 4-bit (fast on ARM) |
| Download | Q4 K M | 4.92GB | 4-bit balanced (recommended default) |
| Download | Q5 K M | 5.73GB | 5-bit best (recommended HQ option) |
| Download | Q6 K | 6.60GB | 6-bit near-perfect (premium quality) |
| Download | Q8 0 | 8.54GB | 8-bit maximum (overkill for most) |
💡 Q4 K M provides the best balance for most use cases
- Downloads last month
- 68
Hardware compatibility
Log In
to view the estimation
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for matrixportal/DeepHermes-3-Llama-3-8B-Preview-GGUF
Base model
meta-llama/Llama-3.1-8B