ImportBot: Import: acceptance checklist for a newly arrived card, @boz._., @matstatman, @darkmaniac7, @globalapathy, @c133, @endsjeremy, @kellertreppe123, @wakeupmbrc1, @_syn_thetic_, @dalzyyy, @zefrench6961, @douya4305, @dottoreargus, @_josh_; repos PixelML/club-170hx, dev-boz/cmp170hx-testsuite, matstatman/gpcprobe; lab notes

2026-10-30T08:53:02Z

Import: acceptance checklist for a newly arrived card, @boz._., @matstatman, @darkmaniac7, @globalapathy, @c133, @endsjeremy, @kellertreppe123, @wakeupmbrc1, @_syn_thetic_, @dalzyyy, @zefrench6961, @douya4305, @dottoreargus, @_____josh_____; repos PixelML/club-170hx, dev-boz/cmp170hx-testsuite, matstatman/gpcprobe; lab notes

← Older revision		Revision as of 08:53, 30 October 2026
Line 18:		Line 18:
	== 3. Look at the card ==		== 3. Look at the card ==
	* Bracket bent? Corrosion on the heatsink, rusted screws? Cards from farms with poor humidity control arrive oxidised; outside corrosion suggests the board may be corroding too. {{Source\|handle=kellertreppe123\|date=2026-10-19\|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1561782970262757537}}<br />{{Source\|handle=wakeupmbrc1\|date=2026-10-19\|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1561814886223450345}}		* Bracket bent? Corrosion on the heatsink, rusted screws? Cards from farms with poor humidity control arrive oxidised; outside corrosion suggests the board may be corroding too. {{Source\|handle=kellertreppe123\|date=2026-10-19\|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1561782970262757537}}<br />{{Source\|handle=wakeupmbrc1\|date=2026-10-19\|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1561814886223450345}}
	* Dirt and missing thermal pads. Cards from ~~one large seller~~ arrived very dirty with pads missing on the back of the PCB and on side components. {{Source\|handle=_syn_thetic_\|date=2026-10-25\|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1563971432869007443}} Note it now; clean and repad after the card passes ([[Cooling and power]]).		* Dirt and missing thermal pads. Cards from Alifond arrived very dirty with pads missing on the back of the PCB and on side components. {{Source\|handle=_syn_thetic_\|date=2026-10-25\|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1563971432869007443}} Note it now; clean and repad after the card passes ([[Cooling and power]]).
	* The board shape: a real 170HX PCB is out of the PCIe CEM spec, with no key notch on the left of the gold fingers, so a different board in a 170HX shell is unlikely. {{Source\|handle=dalzyyy\|date=2026-10-11\|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1558734798107836516}}		* The board shape: a real 170HX PCB is out of the PCIe CEM spec, with no key notch on the left of the gold fingers, so a different board in a 170HX shell is unlikely. {{Source\|handle=dalzyyy\|date=2026-10-11\|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1558734798107836516}}
	* The power connector is present and undamaged. The card takes one 8-pin EPS input; see [[Cooling and power]] before using adapters.		* The power connector is present and undamaged. The card takes one 8-pin EPS input; see [[Cooling and power]] before using adapters.

ImportBot: Import: acceptance checklist for a newly arrived card, @boz._., @matstatman, @darkmaniac7, @globalapathy, @c133, @endsjeremy, @kellertreppe123, @wakeupmbrc1, @_syn_thetic_, @dalzyyy, @zefrench6961, @douya4305, @dottoreargus, @_josh_; repos PixelML/club-170hx, dev-boz/cmp170hx-testsuite, matstatman/gpcprobe; lab notes

2026-10-30T08:03:56Z

New page

{{Status|Reported}} {{Cards|both}}

What to do when a card arrives, in order, so you can keep it with confidence or send it back inside the return window with evidence. The tests themselves are explained on [[Testing and burn-in]]. Why each step matters is on [[Buying]].

Plan about an hour per card for steps 4 to 8, plus the time to install the unlock the first time.

== 1. Before it arrives ==
* Save the listing, the seller's claims and the messages, on the platform you bought from. Keep all messages there; do not move to WhatsApp or email. {{Source|handle=darkmaniac7|date=2026-10-26|note=lab notes}}
* Note the return window and how returns are paid. Buy where the item can be returned, preferably for free. {{Source|handle=endsjeremy|date=2026-10-14|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1560021560658497588}}
* Have a test host ready: Linux, the NVIDIA driver and CUDA toolkit, forced airflow over the card, and an 8-pin EPS power cable (see [[Cooling and power]]). Build the test tools in advance (see [[Testing and burn-in]]).
* Do not solder the x16 cap mod until the card has passed. The mod only changes transfer speed; the tests do not need it. {{Source|handle=boz._.|date=2026-10-09|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1558098091574562848|repo=https://github.com/dev-boz/cmp170hx-testsuite}}.

== 2. Delivery ==
* Film the unboxing in one continuous take, starting from the sealed parcel and its label. {{Source|handle=darkmaniac7|date=2026-10-26|note=lab notes}} The test suite has a run sheet for filming a whole test session in one take. {{Source|handle=boz._.|date=2026-10-09|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1558098091574562848|repo=https://github.com/dev-boz/cmp170hx-testsuite}}.
* {{Status|Warning}} Photograph the shipping label and weigh the parcel. A member's multi-card order arrived as metal plates; the label declared a different item and about half the parcel's real weight. {{Source|handle=darkmaniac7|date=2026-10-26|note=lab notes}}
* Photograph any damage to the box. A card that arrived in a box with a hole and a bent bracket was no longer detected on PCIe; keep the packaging for the insurance or return claim. {{Source|handle=globalapathy|date=2026-10-18|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1561380398091735112}}<br />{{Source|handle=globalapathy|date=2026-10-18|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1561381534022238223}}

== 3. Look at the card ==
* Bracket bent? Corrosion on the heatsink, rusted screws? Cards from farms with poor humidity control arrive oxidised; outside corrosion suggests the board may be corroding too. {{Source|handle=kellertreppe123|date=2026-10-19|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1561782970262757537}}<br />{{Source|handle=wakeupmbrc1|date=2026-10-19|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1561814886223450345}}
* Dirt and missing thermal pads. Cards from one large seller arrived very dirty with pads missing on the back of the PCB and on side components. {{Source|handle=_syn_thetic_|date=2026-10-25|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1563971432869007443}} Note it now; clean and repad after the card passes ([[Cooling and power]]).
* The board shape: a real 170HX PCB is out of the PCIe CEM spec, with no key notch on the left of the gold fingers, so a different board in a 170HX shell is unlikely. {{Source|handle=dalzyyy|date=2026-10-11|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1558734798107836516}}
* The power connector is present and undamaged. The card takes one 8-pin EPS input; see [[Cooling and power]] before using adapters.

== 4. First power-on and identity ==
Cap the power and run the fan at full speed for all tests. {{Source|handle=boz._.|date=2026-10-09|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1558098091574562848|repo=https://github.com/dev-boz/cmp170hx-testsuite}}. Test one card at a time; parallel tests make it hard to tell a bad card from a PSU, riser, board or cooling problem. {{Source|handle=c133|date=2026-10-20|link=https://discord.com/channels/1518634379604136178/1528826330454429706/1562161732137386127|repo=https://github.com/PixelML/club-170hx}}.
<syntaxhighlight lang="bash">
lspci -nn | grep -i 10de # 10de:20c2 = 8 GB card, 10de:2082 = 10 GB card
lspci -nnv -d 10de: | grep -i subsystem
nvidia-smi -q | grep -i -E 'serial|vbios|board part|product name'
sudo nvidia-smi -i 0 -pl 180 # resets at every boot
</syntaxhighlight>
* Compare the PCI ID, subsystem, VBIOS and board part number with [[Which card do I have]]. A normal 8 GB card has board part number <code><nowiki>900-11001-0108-000</nowiki></code>. {{Source|handle=zefrench6961|date=2026-10-19|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1561765346833076396}} A 32 GB engineering-sample card reported subsystem <code><nowiki>10de:1586</nowiki></code>. {{Source|handle=douya4305|date=2026-10-13|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1559698008516337665}}
* Write down the serial number. It ties your test logs to this card.

== 5. Read the card's history ==
Before the unlock, read what the card has been through. Both tools only read.
* <code><nowiki>sudo python3 blackbox.py live</nowiki></code> from [[gpcprobe]] dumps the InfoROM black box: boot count and power-on hours, power-cap history, and a log of Xid errors with timestamps. {{Source|handle=matstatman|date=2026-10-20|link=https://discord.com/channels/1518634379604136178/1518695328008638516/1562128904007843850|repo=https://github.com/matstatman/gpcprobe}}. @globalapathy used @matstatman's tools the day they came out to avoid buying bad cards. {{Source|handle=globalapathy|date=2026-10-20|link=https://discord.com/channels/1518634379604136178/1518695328008638516/1562131178524250145}}
* <code><nowiki>sudo python3 gpc_probe.py</nowiki></code> shows which GPCs and memory partitions are disabled and which are fused defective. {{Source|handle=matstatman|date=2026-10-20|link=https://discord.com/channels/1518634379604136178/1518695328008638516/1562128904007843850|repo=https://github.com/matstatman/gpcprobe}}.
* 10 GB cards: also read the RIR state with the read commands of [[170hx-rir-tool]] (never the write command). Used cards whose RIR records were spent are expected on the market. {{Source|handle=dottoreargus|date=2026-10-20|link=https://discord.com/channels/1518634379604136178/1518695328008638516/1562149898311180342}}

== 6. Unlock and check the result ==
Install the unlock as described on [[Driver unlock]], then do a full power-off and power-on (a cold boot, not a reboot).
<syntaxhighlight lang="bash">
nvidia-smi --query-gpu=index,serial,memory.total,pcie.link.gen.current,pcie.link.width.current,power.limit --format=csv
</syntaxhighlight>
* 8 GB card: <code><nowiki>memory.total</nowiki></code> 65536 MiB. 10 GB card: 40960 MiB. The test suite's identity check passes only on these values with no Xid since boot. {{Source|handle=boz._.|date=2026-10-09|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1558098091574562848|repo=https://github.com/dev-boz/cmp170hx-testsuite}}.
* SM count: 74 on the 8 GB card with cmpunlocker v0.5. An older unlocker shows 70. {{Source|handle=matstatman|date=2026-10-08|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1557782065959669861}}<br />{{Source|handle=matstatman|date=2026-10-08|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1557783127814971503}}
* PCIe: x4 is normal without the cap mod.
* If a card stays at 32 GB, it is a single-rank or PG199-origin board; see [[Buying]].

== 7. Run the tests ==
Run them in this order, one card at a time, as soon as possible after the cold boot. Details, commands and pass rules are on [[Testing and burn-in]].
# Memory: memtest_vulkan (5 minutes) right after a cold boot, then a CUDA test over the full unlocked VRAM.
# Compute: <code><nowiki>gpu_burn -tc</nowiki></code> with 0 errors.
# Tensor-core correctness: identical calculations compared across cards, or against a CPU reference. Cards exist that pass memory tests while their tensor cores return garbage. {{Source|handle=_____josh_____|date=2026-10-08|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1557730223137751122}}
# Throughput: [[mmapeak]] or a PyTorch GEMM benchmark (BF16 or FP16 150 to 200 TFLOPS). {{Source|handle=jimtjames|date=2026-10-11|link=https://discord.com/channels/1518634379604136178/1518695289278566450/1558871079395663902}}
# A real workload that fills the upper VRAM and checks the output.
# The kernel log: no Xid since boot.
A single passing quick memory test is not enough: a card with bad HBM passed a basic Vulkan test 9 times out of 10 and gave all-NaN inference. {{Source|handle=boz._.|date=2026-10-23|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1563148969498910773}}

== 8. Decide ==
{{Status|Warning}} Send the card back if:
* memory size after the unlock is wrong (32 GB on an 8 GB card);
* any memory test reports errors that are not a few fixed addresses (see [[Testing and burn-in#When a card fails]]);
* gpu_burn reports errors, or the tensor results differ from other cards or the reference;
* the card throws GSP or PMU Xids under load, or drops off the bus.
Some owners keep cards with a few bad fixed memory locations and work around them. {{Source|handle=analyticeth|date=2026-10-08|link=https://discord.com/channels/1518634379604136178/1518692084729511967/1557566171195383850}} That is a choice for after the return window, not a reason to skip the return.

If it fails:
* Open the case on the platform early, inside the window, with the logs and the video. On Alibaba, a credit card chargeback recovered money where the platform dispute did not. {{Source|handle=djpandaman|date=2026-10-04|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1556347272445431809}}
* Keep everything: the test suite saves raw logs per serial and date. {{Source|handle=boz._.|date=2026-10-09|link=https://discord.com/channels/1518634379604136178/1528513735575081070/1558098091574562848|repo=https://github.com/dev-boz/cmp170hx-testsuite}}. The club-170hx QC guide lists what to keep: card label, driver and kernel, memory size, test pattern and duration, power limit, peak temperatures, PCIe width and generation, Xid and AER before and after. Do not publish serial numbers or full UUIDs. {{Source|handle=c133|date=2026-10-20|link=https://discord.com/channels/1518634379604136178/1528826330454429706/1562161732137386127|repo=https://github.com/PixelML/club-170hx}}.

== 9. After the card passes ==
* Clean, repad and repaste if needed, set up cooling, and make the power cap persistent ([[Cooling and power]], [[Monitoring]]).
* Do the x16 cap mod if you want it ([[Unlocks]]).
* Keep the test logs. They are your baseline if the card degrades later.

== See also ==
* [[Testing and burn-in]]
* [[Buying]]
* [[Monitoring]]
* [[Which card do I have]]
* [[Troubleshooting]]

{{ImportFooter}}
[[Category:Buying]]
[[Category:8 GB]]
[[Category:10 GB]]

Acceptance checklist - Revision history