Baltor Get started

Models

NVIDIA-Nemotron-3-Super-120B-A12B-BF16

By nvidia. 123.6 billion parameters, a context window of 262,144 tokens and the licence other.

Facts

Released
2026-03-10 the day the repository was first published on Hugging Face Hugging Face, read
Licence
other the licence the model card declares Hugging Face, read
Open weights
Yes the weights are published in this Hugging Face repository Hugging Face, read
Parameters
123.6 billion counted from the safetensors weight files Hugging Face, read
Active parameters
Unknown
Knowledge cutoff
Unknown
Context window
  • 262,144 tokens the maximum position embeddings in the model configuration model configuration, read
Longest output
Unknown
Tool calling
Unknown
Structured output
Unknown
Reasoning controls
Unknown
Inputs and outputs
text in, text out Hugging Face, read
Good for
No source names a use.

Prices

No source lists a price for this model. It may only run on your own hardware.

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
UD-IQ2_XXS49.1 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ2_M49.1 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q2_K_XL50.9 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ3_S52.7 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ3_XXS52.7 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q3_K_M57.5 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q3_K_S57.5 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q3_K_XL58.3 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ4_NL60.1 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-IQ4_XS60.1 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q4_K_S73.6 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
MXFP4_MOE76.4 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q4_K_M76.9 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q4_K_XL78.0 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q5_K_S83.6 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q6_K107 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q6_K_XL110 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
Q8_0120 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
UD-Q8_K_XL123 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers
BF16225 GiBUnknown: no KV cache numbersUnknown: no KV cache numbers

Start it with a local runtime

  • Ollama
    ollama run hf.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF:UD-IQ2_XXS
  • LM Studio
    lms get unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF
lms server start
  • llama.cpp server
    llama-server -hf unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF:UD-IQ2_XXS --jinja
  • vLLM
    vllm serve nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
  • SGLang
    sglang serve --model-path nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 --port 30000

Use it from your harness

No endpoint in this directory serves this model yet.

Published results

These are results other people published. Baltor did not run them and does not rank models by them.