Can the NVIDIA A100 80GB SXM run NVIDIA-Nemotron-3-Super-120B-A12B-BF16?

NVIDIA-Nemotron-3-Super-120B-A12B-BF16 · NVIDIA A100 80GB SXM · 8,192 ctx · whole model residentQ4_K_M sizesize rangeSpeedestimate

IT FITS

Yes. 4 of 9 formats evaluated fit in 80 GB, at 8,192 tokens. No published file exists for this pair, so every size is rebuilt from the pinned architecture. The best quality that fits is Q4_K_M, needing 76.9 GB and running at an estimated 18 tokens per second.

Fitting in memory is not the same as loading. Whether the runtime and version you have supports this architecture and format on this machine has not been tested here.

4/9formats that fit

80 GBdevice memory

76.9 GBneeded at best quality

~18tokens per second, estimatedAbout reading pace

2039GB/s bandwidth

How long a conversation. At Q4_K_M, this pair holds 262,144 tokens of context — roughly 196,608 words — needing 79.0 GB. That is NVIDIA's own configured maximum of 262,144 tokens, not the card running out. A larger device does not extend it; a documented RoPE or YaRN extension might, and is a separate question from this one.

Every format evaluated

No published file exists for this pair, so every size is rebuilt from the pinned architecture. The Basis column says which is which for each row. Decode and first-token figures are calibrated estimates, not runs on this card.

Format	Needs	Of 80 GB	Fits	Decode	First token	Basis
FP16	248.4 GB	310%	short by 168.4 GB	does not run	—	size range
Q8_0	132.5 GB	166%	short by 52.5 GB	does not run	—	size range
Q6_K	102.6 GB	128%	short by 22.6 GB	does not run	—	size range
Q5_K_M	89.3 GB	112%	short by 9.35 GB	does not run	—	size range
Q5_0	87.3 GB	109%	short by 7.31 GB	does not run	—	size range
Q4_K_M	76.9 GB	96%	yes	~18 tok/sAbout reading pace	no comparable peak	size range
Q4_0	73.0 GB	91%	yes	~19 tok/sAbout reading pace	no comparable peak	size range
Q3_K_M	62.9 GB	79%	yes	~22 tok/sAbout reading pace	no comparable peak	size range
Q2_K	50.0 GB	62%	yes	~28 tok/sAbout reading pace	no comparable peak	size range

Sized at 8,192 tokens of context with the whole model resident — weights, the KV cache and the runtime reserve, offload off. Speed is only quoted for a format that fits: a rate for a configuration that cannot load is not a fact about anything.

Why the first-token figure is the same on every row

First token is modelled from the arithmetic the prompt requires, and that count does not change with the weight format — which is why it reads the same on every row. Real prefill does vary by format, because a quantized matmul is a different kernel; this model does not capture that, and the figure should be read as an order of magnitude rather than a ranking between formats.

What the labels mean

published data: Read from a published source — a file's byte count, a model's configuration or a manufacturer's specification — or exact arithmetic on such values. Not a measurement on a machine.
reconstructed size: Weight size reconstructed from the pinned architecture, because no published file exists.
size range: Only a lower and an upper bound are claimed for this weight size.
estimate: Calculated from sourced inputs by a stated method; an estimate, not a measurement.

Change anything

This page fixes the context at 8,192 tokens and one device. Batch, concurrent users, KV-cache format, clusters and rental cost are all in the calculator, already set to this pairing.

Open in the calculator →Everything the NVIDIA A100 80GB SXM runs

Where these numbers come from

NVIDIA-Nemotron-3-Super-120B-A12B-BF16’s architecture is read from its publisher’s own config.json at a pinned revision, and the NVIDIA A100 80GB SXM’s 80 GB and 2039 GB/s come from the manufacturer’s specification. How far each figure can be trusted is published, per format and worst case included, on the accuracy scorecard.

Building this into your own product? A free API key returns exactly these figures, and the widget puts this answer on a product page with one script tag.

Use this answer in your own product

As JSON, from the API

curl -s https://llmbottleneck.com/v1/analyze \
  -H "Authorization: Bearer $LLMB_KEY" -H "content-type: application/json" \
  -d '{"model":"nvidia-nvidia-nemotron-3-super-120b-a12b-bf16","quantization":"Q4_K_M","context":8192,"hardware":"nvidia-a100-80gb-sxm"}'

Same engine, same evidence, every field sourced. Free key in one step →

On your page, as a widget

<script src="https://llmbottleneck.com/widget.js"
  data-model="nvidia-nvidia-nemotron-3-super-120b-a12b-bf16" data-quantization="Q4_K_M"
  data-hardware="nvidia-a100-80gb-sxm" data-context="8192"></script>

No key needed. Unbranded, with your own buy button, on Pro and Business →