NVIDIA CMP 170HX · unlocked when we install it

Unlocked CMP dedicated servers.

NVIDIA built the CMP 170HX for mining and locked the rest of it away: the card showed 8 GB of memory and ran floating-point maths at a crawl. The lock turned out to be software. We install a driver that lifts it, so your server arrives with a card that has 64 GB of very fast memory and runs AI models the way its chip was designed to.

Same card, same chip. The grey part is what NVIDIA left on; the rest is what the driver turns on.

What it is good at now

It was sold for mining. Unlocked, it is an AI card.

A chatbot that is only yours

Run an open model such as Llama, Qwen or Mistral on a server nobody else uses. Prompts, documents and answers stay on your machine instead of going to somebody else’s API.

Big models on one card

A 70-billion-parameter model fits on one unlocked card at 4-bit. On a card that has not been unlocked, the ceiling is a model of about 8 billion.

Room for long conversations

Whatever the model does not use goes to its context, so long documents and long chats keep going instead of running out of room halfway through.

Several models at once

A chat model, an embedding model for search and a small model that routes requests can all stay loaded together, rather than taking turns.

Jobs you would rather not time

One flat monthly price and no meter, on the card or on the bandwidth. Leave a batch running over the weekend and the bill does not move.

The biggest model that fits, by the rule our LLM page uses

8 GB64 GB
4-bit7-8 billion parameters70 billion parameters
8-bit30-34 billion parameters
16-bit13-14 billion parameters

Weights only, with a quarter to a half again kept free for the conversation itself. The full sizing guide is on our LLM page.

The same card, before and after

How much faster, measured by somebody else.

LTT Labs unlocked a CMP 170HX in September 2026 and ran the same models on it both ways. These are their results, not ours. Speeds change with the model and the software, so take them as the size of the jump rather than a number to hold us to.

As NVIDIA shipped itUnlocked

8B model at 4-bit, generating

30 tokens/s
113 tokens/s

LTT Labs, llama.cpp, Granite 4.1 8B Q4_K_M

8B model at 4-bit, reading a prompt

351 tokens/s
2,994 tokens/s

LTT Labs, llama.cpp, pp512

27B model at 4-bit (~16 GB)

does not fit
38 tokens/s

LTT Labs, llama.cpp, Qwen 3.6 27B Q4_K_M

27B model at 8-bit (~29 GB)

does not fit
33 tokens/s

LTT Labs, llama.cpp, Qwen 3.8 27B Q8_0

These numbers come from the LTT Labs write-up of September 2026, which ran llama.cpp on their own test machine. The unlock itself is cmpunlocker, an open-source project by Amogh Munikote.

What happens after you order

Nothing for you to install. That is the point of renting it from us.

  1. 1

    You pick Ubuntu

    Choose Ubuntu 22.04, 24.04 or 26.04 in the configurator. The unlock is a Linux driver, so this is the one choice that matters.

  2. 2

    We fit the card and install

    The card goes in, Ubuntu goes on, and the unlocked driver is built into it for the exact kernel your server will run.

  3. 3

    It starts up unlocked

    The server is switched fully off and back on, which is what the unlock needs, and every card is checked for its full memory before the server is handed over.

  4. 4

    Updates leave it unlocked

    When Ubuntu installs a new kernel, the driver rebuilds itself to match. Type cmp-unlock status whenever you want to see how each card is doing.

Worth knowing before you buy

The catches, up front.

What it costs

The card, the server under it, and nothing on top.

The card is its own line on the invoice and the server is another, so you can see what each one costs. The figure shown is one card in the smallest server that takes it. Add memory, bigger disks or more cards in the configurator and it shows the new total as you go.

There is a one-time setup fee because the card is fitted to your order. Bandwidth is unmetered, US sales tax is added at checkout where it applies, and the monthly price is the same when you renew.

Build my server

$272.67/month

  • The card$189
  • The server$83.67
  • Setup$29 once

Intel Xeon Silver 4110 8 Core 2.10 GHz · 16 GB DDR4 · 2 × SATA-SSD 240 GB (RAID 1) · 1 Gbps

1–4 cards · New York, Bucharest, San Francisco and Miami · 15% off yearly

Questions

What people ask about the unlocked CMP

What does “unlocked” mean for a CMP 170HX?

NVIDIA sold the CMP 170HX as a mining card and switched most of it off in software: it showed 8 GB of memory and did floating-point maths very slowly. A community driver called cmpunlocker switches those parts back on. An unlocked card has 64 GB of memory and runs at the speed of the chip inside it, which is the same chip as an A100.

How much memory will my card have?

64 GB on the 8 GB version of the card, which is what you will see in nvidia-smi. The 10 GB version unlocks to 40 GB, because more than that is not reliable on it. Without the unlocked driver, both show the memory they shipped with.

Do I have to unlock it myself?

No. Order the server with Ubuntu 22.04, 24.04 or 26.04 and it arrives unlocked. We install the driver, build the unlock for your kernel and check each card before handing the server over.

Will it stay unlocked after updates and restarts?

Yes. The unlocked driver loads every time the server starts, and when Ubuntu installs a new kernel the unlock rebuilds itself for it. If a card ever shows 8 GB, switch the server off and on again from the control panel, and tell us if that does not fix it.

Which AI software runs on it?

Anything made for NVIDIA cards: PyTorch, llama.cpp, Ollama, vLLM and the rest. Install the CUDA toolkit with apt install cuda-toolkit. Avoid the packages named cuda and cuda-drivers, which would add a second driver; we set the server to refuse them.

Can I run Windows on it?

You can, but the unlock only exists for Linux, so on Windows the card stays at 8 GB with its original limits. For anything that needs the memory, choose Ubuntu.

How many cards can one server have?

Up to four. Two unlocked cards hold 128 GB between them, enough for a 70-billion-parameter model at 8-bit.

Can I still mine with it?

Yes, unlocking takes nothing away. If mining is the main plan, though, our mining page covers the cards and the costs for that.

Why is there a setup fee?

The card is fitted to your order, which makes the server a custom build, and custom builds carry a one-time setup fee. It is charged once, and the monthly price does not go up when you renew.

Already own a CMP 170HX?

List it on the Primcast marketplace and let AI teams and developers rent it from you by the month, at a price you set.

Go to Marketplace