LLM EXPLORER 65,040 MODELS INDEXED

OSSAS Nemotron 12B by inference-net

By inference-net · 78 downloads
HF Repo ↗ Copy URL

OSSAS Nemotron 12B is an open-source language model by inference-net. Features: 12b LLM, VRAM: 24.6GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.2.

  Arxiv:2502.19413 Base model:finetune:nvidia/nvi... Base model:nvidia/nvidia-nemot...   En   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/inference-net/OSSAS-Nemotron-12B 

OSSAS Nemotron 12B Parameters and Internals

LLM NameOSSAS Nemotron 12B
Repository 🤗https://huggingface.co/inference-net/OSSAS-Nemotron-12B 
Base Model(s)  NVIDIA Nemotron Nano 12B V2   nvidia/NVIDIA-Nemotron-Nano-12B-v2
Model Size12b
Required VRAM24.6 GB
Updated2026-10-20
Maintainerinference-net
Model Typenemotron_h
Model Files  4.8 GB: 1-of-6   4.9 GB: 2-of-6   4.8 GB: 3-of-6   4.9 GB: 4-of-6   3.9 GB: 5-of-6   1.3 GB: 6-of-6   49.2 GB   24.6 GB   0.0 GB   0.0 GB
Supported Languagesen
Model ArchitectureNemotronHForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.55.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<SPECIAL_12>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to OSSAS Nemotron 12B

Best Alternatives
Context / RAM
Downloads
Likes
NVIDIA Nemotron Nano 9B V2128K / 17.7 GB301038506
NVIDIA Nemotron Nano 12B V2128K / 24.6 GB199598165
...IDIA Nemotron Nano 12B V2 Base128K / 24.6 GB360691
Note: green Score (e.g. "73.2") means that the model is better than inference-net/OSSAS-Nemotron-12B.