Views
No views yet
🎯 GGUF Conversion of the original AEON-7/Nemotron-3-Nano-Omni-AEON-Ultimate-Uncensored-BF16
| File | Format | Size | Description |
|---|---|---|---|
Nemotron-3-Nano-Omni-AEON-Uncensored-BF16.gguf | BF16 | ~59GB | Full precision LLM weights |
Nemotron-3-Nano-Omni-AEON-Uncensored-Q6_K.gguf | Q6_K | ~32GB | Quantized LLM weights (recommended) |
mmproj-Nemotron-3-Nano-Omni-BF16.gguf | BF16 | ~1.5GB | Vision encoder projection |
MEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEMEM*EMEMEMEME
M = Mamba2 (SSM)E = Expert (Mixture of Experts)* = Attention1./llama-cli \
2 -m Nemotron-3-Nano-Omni-AEON-Uncensored-Q6_K.gguf \
3 -p "Hello, how are you?" \
4 -n 2561./llama-llava-cli \
2 -m Nemotron-3-Nano-Omni-AEON-Uncensored-Q6_K.gguf \
3 --mmproj mmproj-Nemotron-3-Nano-Omni-BF16.gguf \
4 --image image.jpg \
5 -p "Describe this image in detail."| Step | Tool | Details |
|---|---|---|
| LLM Extraction | Python safetensors | Extracted language_model.* from omni checkpoint |
| GGUF Conversion | convert_hf_to_gguf.py | llama.cpp — NemotronHForCausalLM → BF16 GGUF |
| Quantization | llama-quantize | BF16 → Q6_K |
| mmproj | convert_hf_to_gguf.py --mmproj | NemotronNanoV2VLModel — ViT + projector → BF16 |
| Role | Entity |
|---|---|
| 🧠 Original Model | AEON-7 |
| 📐 Architecture | NVIDIA NemotronH |
| 🔧 GGUF Conversion | @hotdogs |
| 🛠️ Tools | llama.cpp by Georgi Gerganov & contributors |
💡 Note: This repo contains only GGUF format files converted from the original AEON-7 model. For the original PyTorch/SafeTensors weights, please visit the source model.