Skip to content
Local AI Wizard
Your machine
Theme

Nemotron 3 Super 120B A12B

NVIDIA · nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4

Q4 file 82.5 GB (UD-Q4_K_M) · runs well from 128 GB · Weights license: Publisher terms: NVIDIA Nemotron Open Model License

Measured speed15–15 tok/sUD-Q4_K_XL · 1 machine · 2 sources · all rows
Memory needed~90 GBQ4 weights + working room, before the machine's reserve
Parameters120 Bmanufacturer specification · 12B active
Context262,144 tokensPublished for this model

Quality

No result in LiveBench 2026-06-25, LMArena 2026-10-22 Not in LiveBench 2026-06-25 or LMArena 2026-10-22

Reported by the publisher

20 results · NVIDIA's model card · read 2026-10-25
MMLU-Pro
83.33General Knowledge
HMMT Feb25 (with tools)
95.36Reasoning
GPQA (no tools)
79.42Reasoning
LiveCodeBench (v6 2024-08↔2025-05)
78.44Reasoning
LiveCodeBench (v5 2024-07↔2024-12)
80.56Reasoning
SciCode (subtask)
40.83Reasoning
HLE (no tools)
17.42Reasoning
Terminal Bench (hard subset)
24.48Agentic
Every reported result20
Airline
54.75TauBench V2
Retail
63.38TauBench V2
Telecom
63.27TauBench V2
Average
60.46TauBench V2
IFBench (prompt)
73.30Chat & Instruction Following
Scale AI Multi-Challenge
52.8Chat & Instruction Following
Arena-Hard-V2 (Hard Prompt)
76.00Chat & Instruction Following
AA-LCR
58.06Long Context
RULER-500 @ 128k (500 samples per task)
95.99Long Context
RULER-500 @ 256k (500 samples per task)
96.52Long Context
RULER-500 @ 512k (500 samples per task)
96.23Long Context
MMLU-ProX (avg over languages)
79.37Multilingual
Across Nemotron 3 sizes2 shared results · same publisher and settings
Nemotron 3: results the publisher reports for each size under the same settings
Benchmark (publisher settings)Nano 30B A3BSuper 120B A12BUltra 550B A55B
IFBench (prompt) · Chat & Instruction FollowingThis size's card does not report this result under these settings73.3082.3
AA-LCR · Long ContextThis size's card does not report this result under these settings58.0665.5

Values as printed on the card, with the publisher's own settings (card section: License/Terms of Use › Benchmarks); column “Nemotron-3-Super NVFP4”. Not comparable across publishers and not used in any ranking. Model card

Run it

Run it

File UD-Q4_K_M · 82.5 GB · 3 parts · unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF · What is Q4?

Measured 15–15 tok/s · UD-Q4_K_XL · 1 machine · 2 sources · all rows

llama-server -hf unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF:UD-Q4_K_M
  1. Install llama.cpp
  2. Run the command above
  3. Ask at localhost:8080: Explain what a context window is, in two sentences.

Runs on

Fast memory holds it 14

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 14

One memory tier short 1

The same machines with the next memory size up would hold it in fast memory.

Nemotron 3 Super 120B A12B is a text model from NVIDIA with 120B parameters, 12B of them active per token (mixture of experts). It was released on March 11, 2026 and reads up to 262,144 tokens of context. Its Q4 weights plus working room come to about 90 GB before the machine's reserve; the smallest reference machine whose fast memory holds that is Mac Studio M5 Max · 128 GB unified (~98 GB with its reserve). We collected 25 downloadable GGUF and MLX files from 2 publisher sources; the most downloaded GGUF source is unsloth's (212.7K downloads on the Hub). It has no result in LiveBench 2026-06-25, so no quality score is shown.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.

On the reference machines

Nemotron 3 Super 120B A12B on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~92 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 16 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~94 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 24 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~96 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M4 · 32 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~98 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac mini M5 Pro · 64 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~98 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
Mac Studio M5 Max · 128 GB unifiedFast memory holds itUD-IQ4_XSGGUF · 64.5 GB · needs ~86 GB262,144 tokens~98 GBFast memory holds itUD-IQ4_XSGGUF · 64.5 GB · needs ~86 GB262,144 tokens
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itQ8_0GGUF · 128.5 GB · needs ~163 GB262,144 tokens~98 GBFast memory holds itQ8_0GGUF · 128.5 GB · needs ~163 GB262,144 tokens
RTX 4060 · 8 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~92 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 3060 · 12 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~92 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5080 · 16 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~92 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 4090 · 24 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~92 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
RTX 5090 · 32 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column~92 GBLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column
DGX H100 · 8 × 80 GBFast memory holds itQ8_0GGUF · 128.5 GB · needs ~171 GB262,144 tokens~106 GBFast memory holds itQ8_0GGUF · 128.5 GB · needs ~171 GB262,144 tokens

The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.

Plan another quantization or context

Consider it for

Compare Nemotron 3 Super 120B A12B using its publisher card. No overall score appears in the LiveBench 2026-06-25 snapshot.

Check first

The Q4 weights plus working room come to about 90 GB from 120B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Versions to download

Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth (212.7K Hub downloads), at UD-Q4_K_M. On a Mac it opens on the most downloaded MLX source. Sizes are the Hub's published bytes. What is Q4?

unsloth · 212.7K downloads

unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF · UD-Q4_K_M/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-00001-of-00003.gguf · 82.5 GB

Run this file

llama-server -hf unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF:UD-Q4_K_M
lms get https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF
  • Ollama: Ollama's documented hf.co form covers single-file GGUFs; this file has 3 parts
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)

Fine-tunes, adapters and other versions17 fine-tunes
Quantized versions
57
Fine-tunes
17
Adapters · merges
152 · 0

Browse them on the Hugging Face model tree · read 2026-10-23

Uncensored and abliterated versions0

Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.

0 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).

Measured speed

Tokens per second by machine

Output tok/s · 2 machines · every row in the table · What is a token?

DGX Spark · Q4_K, 19.94 ± 0.16 · Q4_K (reported as 'Q4_K' by llama-bench; GGUF from ggml-org) · llama.cpp CUDA · llama.cpp build 04a65daab (8268); n_ubatch=2048; flash attention=1 (llama-bench)19.9
Framework Desktop 128GB · UD-Q4_K_XL, 14.86 ± 0.06 · UD-Q4_K_XL (llama-bench: Q4_K - Medium, 78.02 GiB) · llama.cpp Vulkan (Mesa RADV, toolbox vulkan_radv) · llama.cpp build 1a68ec937 (9193); -ngl 99, -fa 1, mmap 0 (llama-bench)14.9
Framework Desktop 128GB · UD-Q4_K_XL, 14.85 ± 0.04 · UD-Q4_K_XL (llama-bench: Q4_K - Medium, 78.02 GiB) · llama.cpp ROCm 7.2.3 (toolbox rocm-7.2.3) · llama.cpp build 1a68ec937 (9193); -ngl 99, -fa 1, mmap 0 (llama-bench)14.9
Measured speed
DGX SparkDGX Spark · 1× NVIDIA GB10 · 128 GB unified19.94 ± 0.16Q4_K (reported as 'Q4_K' by llama-bench; GGUF from ggml-org)0 / 32 · Single llama-bench process; server concurrency not measuredllama.cpp CUDAllama.cpp build 04a65daab (8268); n_ubatch=2048; flash attention=1 (llama-bench)Flash Attention enabledggml-org/Nemotron-3-Super-120B-GGUF · Q4_K (65.10 GiB); not the NVFP4 checkpoint linked on the model pagellama.cpp benches/nemotron · DGX Spark · 2026-10-09
Framework Desktop 128GBFramework Desktop · AMD Ryzen AI Max+ 395 (Radeon 8060S) · 128 GB unified14.86 ± 0.06UD-Q4_K_XL (llama-bench: Q4_K - Medium, 78.02 GiB)0 / 128 · Single llama-bench process; server concurrency not measuredllama.cpp Vulkan (Mesa RADV, toolbox vulkan_radv)llama.cpp build 1a68ec937 (9193); -ngl 99, -fa 1, mmap 0 (llama-bench)Flash Attention enabledNVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-00001-of-00003.gguf (Unsloth UD-Q4_K_XL, 78.02 GiB)kyuz0/amd-strix-halo-toolboxes raw llama-bench log (GitHub) · community benchmark · 2026-10-09
Framework Desktop 128GBFramework Desktop · AMD Ryzen AI Max+ 395 (Radeon 8060S) · 128 GB unified14.85 ± 0.04UD-Q4_K_XL (llama-bench: Q4_K - Medium, 78.02 GiB)0 / 128 · Single llama-bench process; server concurrency not measuredllama.cpp ROCm 7.2.3 (toolbox rocm-7.2.3)llama.cpp build 1a68ec937 (9193); -ngl 99, -fa 1, mmap 0 (llama-bench)Flash Attention enabledNVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-00001-of-00003.gguf (Unsloth UD-Q4_K_XL, 78.02 GiB)kyuz0/amd-strix-halo-toolboxes raw llama-bench log (GitHub) · community benchmark · 2026-10-09

Sources: llama.cpp benches/nemotron · DGX Spark · kyuz0/amd-strix-halo-toolboxes raw llama-bench log (GitHub) · community benchmark · kyuz0/amd-strix-halo-toolboxes raw llama-bench log (GitHub) · community benchmark · not estimated

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Evidence level: Generic estimate only; no execution reproduced by this site.

Publisher sampling defaults
temperature 1 · top_p 0.95generation_config.json · read 2026-10-23source
Chat template markers
tool calls · thinkingmarkers found in the template, not a test of the feature · read 2026-10-23source
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task and modality
language and reasoning · text
Count and basis
120B · manufacturer specification · 12B active
Context
262,144 tokens published for this model
Architecture
MoE
Released
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 model card (Hugging Face) · read 2026-10-09source
Runtime and precision
No local execution verified.
Languages
en, fr, es, it, de, ja, zhModel card metadata · read 2026-10-25source
Commercial use
License text not read: nvidia.com was unreachable on 2026-10-18 and the repositories ship no copy
Every stored field12 fields
Revision checked
ff433f5493e25d631c9f12b5d55c674229923d02
Architecture
NemotronHForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Repository created
2026-03-10creation is not the model's release
Repository updated
2026-08-24a commit is not a release date
Hub downloads (30 days) · likes
535,065 · 455this repository only · read 2026-10-25
Read from the Hub page
transformers class, task tags, license nameHub overview and file listing · read 2026-10-18
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-09-26.