Downloads · 30 days
26
8% of all-time downloads
blobbybob/Nemotron-3-Super-120B-A12B-FP8-Claude-4.6-Opus-Reasoning-Distilled
Nemotron-3-Super-120B-A12B-FP8-Claude-4.6-Opus-Reasoning-Distilled is a text generation model from blobbybob. Use it when you need the model to write or continue text. The card lists the license as other.
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 datas…
Downloads · 30 days
26
8% of all-time downloads
All-time downloads
324
Public
Parameters
121B
235 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors235 GB · 100%
How the weights are stored.
BF16114B · 94%
From the Hugging Face model README
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).
A fine-tuned version of NVIDIA Nemotron-3-Super-120B-A12B with enhanced reasoning capabilities, distilled from Claude Opus 4.6 reasoning traces.
| 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) |
| Precision | FP8 (NVIDIA ModelOpt) |
| 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 |
This model has been fine-tuned on 2,326 high-quality reasoning traces from Claude Opus 4.6. The model produces structured reasoning with <think> tags before answering, similar to o1/reasoning-style models.
from vllm import LLM, SamplingParams
llm = LLM(
model="blobbybob/Nemotron-3-Super-120B-A12B-FP8-Claude-4.6-Opus-Reasoning-Distilled",
dtype="auto",
tensor_parallel_size=2,
max_model_len=4096,
trust_remote_code=True,
)
sampling = SamplingParams(temperature=1.0, top_p=0.955, max_tokens=2048)
messages = [
{"role": "system", "content": "You are a helpful reasoning assistant. Think step by step before answering."},
{"role": "user", "content": "What is the sum of all prime numbers less than 20?"},
]
tokenizer = llm.get_tokenizer()
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = llm.generate([prompt], sampling)
print(outputs[0].outputs[0].text)
This checkpoint uses NVIDIA ModelOpt FP8 quantization. vLLM auto-detects the format via hf_quant_config.json.
mamba-ssm installedThis model inherits the NVIDIA Open Model License from the base model.