Can I run NVIDIA Nemotron 3.5 Lightning on an RX 7900 XTX?
Key facts
Yes. NVIDIA Nemotron 3.5 Lightning runs on an RX 7900 XTX: the whole model fits in its graphics memory.
It needs about 19.8 GB at standard quality (estimate). Checked . ggml-org Q4_0 GGUF (official ggml-org repo; not Q4_K_M).
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.
How much memory it needs
It uses about 84% of the memory that is free on this card.
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.
What an RX 7900 XTX costs
Radeon RX 7900 XTX 24GB$1,404€1,254used (3-month median)
EU shops · Shown to visitors in Europe.US shops · Shown to visitors outside Europe.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
Price details
$1,404€1,254
How we priced this
Used price, the typical price over the last three months.
Source: GPU PRIX, checked 17 Oct 2026.
New in stock, €3,972 at GPU PRIX on 17 Oct 2026 (unusually high). Source: GPU PRIX, 17 Oct 2026. More than 1.5 times the typical price of €1,254, so we do not use it as the main price.
€1,254 is the typical price over the past 3 months on GPU PRIX, checked 17 Oct 2026. The only board in stock (an ASUS TUF Gaming at €3,972) cost more than 1.5 times that, and cheaper boards, such as an XFX Speedster at €1,049, were out of stock.
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.
The cheapest graphics card on our list that also runs it (it still needs the rest of a PC): GeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings).
The cheapest complete machine that runs it: Mac mini M6 32GB, about $1,416€1,530.
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.
NVIDIA Nemotron 3.5 Lightning on other graphics cards
Runs well6
The whole model fits in the graphics memory.
Doesn't fit4
Not enough graphics memory: it needs about 19.8 GB.
- RTX 3060 12GBhas 12 GB
- RTX 4060 Ti 16GBhas 16 GB
- RTX 5080has 16 GB
- RX 9060 XT 16GBhas 16 GB
More about the model itself, what it is good at and its licence: NVIDIA Nemotron 3.5 Lightning.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this card.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Runs | 18.9 GBmeasured file | 0.1 GB | 0.8 GB | 19.8 GB | 23.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Runs | 21.3 GB | 0.1 GB | 0.8 GB | 22.2 GB | 23.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Doesn't fit | 32.1 GB | 0.1 GB | 0.8 GB | 33.0 GB | 23.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Doesn't fit | 60.0 GB | 0.1 GB | 0.8 GB | 60.9 GB | 23.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Runs | 18.9 GBmeasured file | 0.2 GB | 0.8 GB | 19.9 GB | 23.4 GB |
speed: not estimated for MoE yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . ggml-org Q4_0 GGUF (official ggml-org repo; not Q4_K_M).
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.
Measured NVIDIA Nemotron 3.5 Lightning on an RX 7900 XTX yourself? Send us your llama-bench result.
Questions
- Can I run NVIDIA Nemotron 3.5 Lightning on an RX 7900 XTX?
- Yes. NVIDIA Nemotron 3.5 Lightning runs on an RX 7900 XTX: the whole model fits in its graphics memory.
- How much memory does NVIDIA Nemotron 3.5 Lightning need?
- About 19.8 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 18.9 GB for the model file (measured), 0.1 GB to hold the conversation and 0.8 GB of working space.
- How fast is NVIDIA Nemotron 3.5 Lightning on an RX 7900 XTX?
- 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.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate