Views
No views yet
Beta Release - This is a beta release. A v2 is expected with more training data and improved training methodology. As of now, this model is fine-tuned exclusively on the nohurry/Opus-4.6-Reasoning-3000x-filtered dataset (2,326 reasoning traces from Claude Opus 4.6).
| Quantization | File | Size | Description |
|---|---|---|---|
| Q4_K_M | nemotron-120b-q4-k-m.gguf | ~50 GB | Best balance of quality and size. Medium quality, recommended for most users. |
| Q8_0 | nemotron-120b-q8-0.gguf | ~120 GB | Near-lossless quantization. Best quality, requires more RAM. |
| Property | Value |
|---|---|
| Base Model | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| Architecture | Nemotron-H (Mamba-2 SSM + MoE + Attention hybrid) |
| Parameters | 120B total / 12B active (MoE) |
| Fine-tuning Method | LoRA (r=32, alpha=64) merged into base weights |
| Training Data | nohurry/Opus-4.6-Reasoning-3000x-filtered |
| Epochs | 3 |
| Final Training Loss | 0.42 |
<think> tags before answering, similar to o1/reasoning-style models.1# Download the Q4_K_M quantization
2huggingface-cli download blobbybob/Nemotron-3-Super-120B-A12B-GGUF-Claude-4.6-Opus-Reasoning-Distilled \
3 nemotron-120b-q4-k-m.gguf --local-dir ./models
4
5# Run inference
6./llama-cli -m ./models/nemotron-120b-q4-k-m.gguf \
7 -p "<|im_start|>system\nYou are a helpful reasoning assistant. Think step by step before answering.<|im_end|>\n<|im_start|>user\nWhat is 7 * 13?<|im_end|>\n<|im_start|>assistant\n" \
8 --temp 1.0 --top-p 0.95 -n 512Modelfile:FROM ./nemotron-120b-q4-k-m.gguf
PARAMETER temperature 1.0
PARAMETER top_p 0.95
SYSTEM You are a helpful reasoning assistant. Think step by step before answering.1ollama create nemotron-reasoning -f Modelfile
2ollama run nemotron-reasoning "What is the sum of all prime numbers less than 20?"temperature=1.0 and top_p=0.95 across all tasks — reasoning, tool calling, and general chat alike.