localLLMrig
Menu

Which GPUs and Macs run NVIDIA Nemotron 3.5 Lightning?

Key facts

NVIDIA Nemotron 3.5 Lightning needs about 20 GB of graphics memory. It runs on 6 of the 10 graphics card setups on this page, such as the RTX 3090.

About 19.8 GB at Q4_0, our estimate. Checked . ggml-org Q4_0 GGUF (official ggml-org repo; not Q4_K_M).

Try NVIDIA Nemotron 3.5 Lightning free in your browser, no login, no install

The cheapest graphics card on our list that runs it (it still needs the rest of a PC): GeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings).

Our price is for a used card. These shops mostly sell new ones, so their price can be higher.

EU shops · Shown to visitors in Europe.

US shops · Shown to visitors outside Europe.

If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work

As an Amazon Associate I earn from qualifying purchases.

Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.

Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.

We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate

The cheapest complete machine that runs it: Mac mini M6 32GB, about $1,416€1,530.

We don't give a speed for this model yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.

Find hardware for NVIDIA Nemotron 3.5 LightningAbout this model

LIVE IN BROWSER · $0 · NO LOGIN

Test NVIDIA Nemotron 3.5 Lightning free in your browser before downloading 19 GB

Open full 8-model playground ↗

Click a starter prompt below or type your own question to watch Nemotron 3.5 Lightning stream side by side against Gemma 4 31B right on this page:

Watch on YouTube ↗

Watch: 8 open LLMs vs 1 trick question (24s real-time screen recording)

Unedited recording of the free multi-model playground on localLLMrig.com running Gemma 4 31B, NVIDIA Nemotron 3.5 Lightning, Recursive Flint, and Gemma 4 26B A4B side by side on the classic €1.10 bat-and-ball question — then showing the cheapest Mac mini or GPU that runs the winner locally. Watch on YouTube (@localllmrig) ↗

Get a 1-line alert when a faster quant for NVIDIA Nemotron 3.5 Lightning drops — or when GPUs that run it drop >10%

Get a 1-line alert when a new open-weight model fits 24 GB VRAM (19.8 GB at Q4 for NVIDIA Nemotron 3.5 Lightning) or when used RTX 3090 / 4090 & Mac Studio prices drop >10% — weekly, zero spam.

Which graphics cards run it

Seven popular graphics cards and two PCs with two cards each, at the standard quality (Q4). Click one for the full answer: memory, speed and price.

Runs well6

The whole model fits in the graphics memory.

Doesn't fit4

Not enough graphics memory: it needs about 19.8 GB. In a PC with enough normal memory it runs slowly: Budget PC with RTX 3060 12GB, about $1,310€1,361 (with a used graphics card).

Every model on every card

Which Macs and mini PCs run it

Macs and mini PCs from the picker, at the standard quality (Q4). A Mac shares its memory with the rest of the computer. Each name opens that machine's page.

Runs well11

The whole model fits in the memory the graphics can use.

Doesn't fit1

Not enough shared memory: it needs about 19.8 GB.

Cheapest hardware for each size

From all 43 graphics cards, PCs and Macs on our list. "Runs slowly" means part of the model runs from normal memory: cheaper, but much slower. A smaller download needs less memory and answers a little less well.

Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.

Prices moved: see Building a local LLM rig in the RAMageddon.

About NVIDIA Nemotron 3.5 Lightning

30B total, 3B active. Parameter count is an estimate. More parameters usually means a smarter model that needs more memory.

Licence:
OpenMDW-1.1 source
Longest conversation:
about 393 pages of text (262,144 tokens)
Input:
text
Sources and method

NVIDIA's hybrid Mamba and Transformer mixture of experts: 30B total, 3B active, open weights under OpenMDW-1.1. The card says up to 1M tokens; the config and the single-H100 recipe use 262,144, which is the context stored here. The stack is 52 blocks (23 Mamba, 23 mixture-of-experts, 6 attention). Our conversation-memory estimate uses only those 6 attention blocks and does not model the Mamba state.

Ran NVIDIA Nemotron 3.5 Lightning on your own hardware? Send us your llama-bench result.

Parameter source · Architecture source · Model page

Memory at each quality level

Each download of NVIDIA Nemotron 3.5 Lightning is a different size. The total adds the file, the memory a conversation of about 12 pages of text (8,192 tokens) takes, and 0.8 GB of working space. A measured file size is labelled; the rest is our estimate. The last column is the cheapest machine that holds the total.

Swipe the table sideways to see every column, up to the cheapest machine.

Memory per quant for NVIDIA Nemotron 3.5 Lightning
Quality (file)File sizeConversationWorking spaceTotalCheapest machine that holds it
BF1663.18 GBmeasured GGUF0.1 GB0.8 GB64.0 GBMac Studio M4 Max 128GB, $3,683€3,290 (used), price unverified
Q8_033.59 GBmeasured GGUF0.1 GB0.8 GB34.4 GBMac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified
UD-Q5_K_XL30.41 GBmeasured GGUF0.1 GB0.8 GB31.3 GBMac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified
UD-Q4_K_XL25.51 GBmeasured GGUF0.1 GB0.8 GB26.4 GBMac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified
UD-Q3_K_XL21.24 GBmeasured GGUF0.1 GB0.8 GB22.1 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)
UD-IQ2_M19.43 GBmeasured GGUF0.1 GB0.8 GB20.3 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)
Q4_018.90 GBmeasured GGUF0.1 GB0.8 GB19.8 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)

speed: not estimated for MoE yet.

Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate

Questions

Can I test NVIDIA Nemotron 3.5 Lightning online for free in my browser before downloading 19 GB?
Yes. NVIDIA Nemotron 3.5 Lightning (30B total, 3B active, parameter count is an estimate) is one of the 10 free open models at https://localllmrig.com/ and in the inline test box on https://localllmrig.com/can-i-run/nemotron-3.5-lightning. You can compare it side by side against Gemma 4 31B (https://localllmrig.com/can-i-run/gemma-4-31b), Recursive Flint (https://localllmrig.com/can-i-run/flint), Laguna S 2.1 (https://localllmrig.com/can-i-run/laguna-s-2.1) for $0 with no account.
Can I run NVIDIA Nemotron 3.5 Lightning on 24GB?
Yes, by our estimate. At Q4_0 (18.9 GB measured GGUF + 0.05 GB conversation memory at 8,192 tokens + 0.80 GB working space = 19.75 GB / 19.8 GB total estimate), NVIDIA Nemotron 3.5 Lightning fits inside the 23.4 GB usable memory of a 24 GB card. The cheapest 24 GB card on our list is GeForce RTX 3090 24GB at €1,246 / $1,395. A 24 GB card also holds UD-Q3_K_XL (21.24 GB measured GGUF, 22.1 GB total estimate) and UD-IQ2_M (19.43 GB measured GGUF, 20.3 GB total estimate).
Can I run NVIDIA Nemotron 3.5 Lightning on a 16GB or 32GB GPU?
On a 16 GB GPU (15.4 GB usable), none of the listed GGUF files fit in VRAM, so the model has to offload layers to system RAM. On a 32 GB GPU (31.4 GB usable, GeForce RTX 5090 32GB), UD-Q5_K_XL (30.41 GB measured GGUF, 31.3 GB total estimate), UD-Q4_K_XL (25.51 GB measured GGUF, 26.4 GB total estimate), UD-Q3_K_XL (21.24 GB measured GGUF, 22.1 GB total estimate), UD-IQ2_M (19.43 GB measured GGUF, 20.3 GB total estimate), Q4_0 (18.9 GB measured GGUF, 19.8 GB total estimate) fit in VRAM.
Can I run NVIDIA Nemotron 3.5 Lightning on a 128GB Mac?
Yes, by our estimate. NVIDIA Nemotron 3.5 Lightning fits on Mac Studio M4 Max 128GB and Mac Studio M5 Max 128GB (96.0 GB usable of 128 GB, which holds BF16 (63.18 GB measured GGUF, 64.0 GB total estimate)). At Q4_0 (19.8 GB estimate), the cheapest 32 GB Mac that holds it is Mac mini M6 32GB (21.3 GB usable, €1,530 / $1,416, price unverified). Mac mini M4 Pro 64GB (48.0 GB usable, €1,890 / $2,116, price unverified) holds Q8_0 (33.59 GB measured GGUF, 34.4 GB total estimate).
How fast is NVIDIA Nemotron 3.5 Lightning on an RTX 5090?
We don't give a speed for this model yet. This model only uses part of itself for each word (3B active of 30B total, a mixture of experts), and our speed estimate does not handle that yet.
Why is NVIDIA Nemotron 3.5 Lightning's conversation cache estimate so small (0.05 GB at 8,192), and what is its license?
The catalog counts conversation memory for 6 attention blocks (2 key-value heads, head size 128), about 0.05 GB at 8,192 tokens (0.1 GB rounded). The model notes describe a 52-block hybrid stack (23 Mamba blocks, 23 mixture-of-experts blocks, and 6 attention blocks). Licence: OpenMDW-1.1, with 262,144 tokens stored as the context length. The model notes say the card claims up to 1M tokens; the context stored here is the config figure.
Can I try NVIDIA Nemotron 3.5 Lightning online for free?
Yes. NVIDIA Nemotron 3.5 Lightning is on the free chat on the home page. Pick it there, ask a question, and read the answer in your browser. No login and no install.
Do I need a GPU to test it?
No. The free chat runs in your browser. It does not download the model and it does not use a graphics card on your computer. A graphics card only matters if you run the model yourself.
Do I need an account to try NVIDIA Nemotron 3.5 Lightning?
No. The free chat needs no account and no login.