What are the hardware requirements for TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0?

TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0 requires approximately 36.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0 and how large is it?

TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0 is developed by 0xBakeer, a model with 120b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0?

TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0 by 0xBakeer — VRAM 36.6GB

Name: TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0
Author: 0xBakeer

TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0 is an open-source language model by 0xBakeer. Features: 120b LLM, VRAM: 36.6GB, License: other, LLM Explorer Score: 0.3.

Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv... Conversational Custom code Exl3 Exllamav3 Mamba2 Moe Mtp Nemotron Nemotron-3.5 Nemotron h Nemotron h omni Quantized Region:us Safetensors Sharded Tandemllm Tensorflow

Model Card on HF 🤗: https://huggingface.co/0xBakeer/TandemLLM-Nemotron-3.5-Super-VL-120B-A12B-EXL3-2.0

TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0 Parameters and Internals

LLM Name	TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0
Repository 🤗	https://huggingface.co/0xBakeer/TandemLLM-Nemotron-3.5-Super-VL-120B-A12B-EXL3-2.0
Base Model(s)	nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
Model Size	120b
Required VRAM	36.6 GB
Updated	2026-10-21
Maintainer	0xBakeer
Model Type	nemotron_h_omni
Model Files	8.3 GB: 1-of-5 8.0 GB: 2-of-5 8.0 GB: 3-of-5 8.0 GB: 4-of-5 4.3 GB: 5-of-5
Model Architecture	NemotronH_Omni_Reasoning_V3
License	other
Model Max Length	1048576
Transformers Version	5.12.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|im_end\|>

Rank the TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to TandemLLM Nemotron 3.5 Super VL 120B A12B EXL3 2.0

Best Alternatives	Context / RAM	Downloads	Likes
...n 3.5 Super VL 120B A12B NVFP4	0K / 30 GB	9322	169
...on 3.5 Super VL 120B A12B BF16	0K / 148 GB	15095	78
...5 Super VL 120B A12B Base BF16	0K / 144 GB	1030	51
...Nemotron 3.5 Bolt 74B A9B BF16	0K / 82.8 GB	2193	40
...n 3.5 Super VL 120B A12B NVFP4	0K / 31.7 GB	1256	3
...emotron 3.5 Super VL 120B A12B	0K / 160 GB	406	5
....5 Super VL 120B A12B EXL3 4.0	0K / 64.7 GB	182	1
...5 Super VL 120B A12B EXL3 3bpw	0K / 44.3 GB	173	1
....5 Super VL 120B A12B MLX 4bit	1024K / 69.4 GB	965	2

Note: green Score (e.g. "73.2") means that the model is better than 0xBakeer/TandemLLM-Nemotron-3.5-Super-VL-120B-A12B-EXL3-2.0.