VRAMGlass contains affiliate links. As an eBay Partner, we may be compensated if you make a purchase.As an eBay Partner, we may be compensated.Learn more

GPUs tracked57Price history49 daysPrice points (24h)39,704 pointsBiggest 24h dropRadeon RX 7900 XTX-3.8%Biggest 24h riseCMP 170HX 40GB+19.8%Updated
$ USD

CMP 170HX 40GB Price & Used Prices: Which Local LLMs Can It Run?

The CMP 170HX 40GB is a modded 2021 NVIDIA mining card; a driver patch unlocks 40GB for models up to 35B at 8-bit. The patch is Linux-only.

eBay

CMP 170HX 40GB price history

Current$2,934+19.76%
eBay
Price updated
$3,138$2,879$2,620$2,361$2,102
Low $2,250High $2,990
Oct 14, 06:00 PMOct 15, 06:00 AMOct 15, 06:00 PM

As an eBay Partner, VRAMGlass may be compensated if you buy through the eBay links on this page. The price you pay stays the same.

Full CMP 170HX 40GB specifications

  • Memory40 GB · HBM2e
  • Bandwidth1,560 GB/s
  • FP16 / BF16202 TFLOPS
  • INT8404 TOPS
Bus width
5,120-bit
Architecture
Ampere (GA100)
Cores
4,480
Tensor cores
280
Ecosystem
CUDA
Interface
PCIe 2.0 x4
NVLink
Not supported
Power
250 W
Power connector
8-pin CPU (EPS-12V)
Slots
2
Length
267 mm
Type
Data center
Launch date
Sep 1, 2021

Best CMP 170HX 40GB deals on eBay

Hand-picked deals from trusted eBay sellers. Shop with confidence.

As an eBay Partner, VRAMGlass may be compensated if you buy through the eBay links on this page. The price you pay stays the same.

What LLMs can a single CMP 170HX 40GB run?

Unlocked, one CMP 170HX 40GB fits every model up to 35B at 8-bit, with 30B-class MoE near 130 tokens/s. 70B-class dense needs two cards.

ModelSizeRuns?Speed t/sMax context
Qwen3.5 9B9.7B5.7 GBRuns159.3256K
Gemma 4 12B12B7.1 GBRuns132.8256K
Gemma 4 26B A4B25.2B (3.8B active)16.9 GBRuns143.2256K
Qwen3.6 27B27.8B16.8 GBRuns63.8256K
Qwen3.8 27B27.8B16.5 GBRuns64.9256K
GLM 4.7 Flash30B (3B active)18.3 GBRuns156198K
Gemma 4 31B30.7B18.3 GBRuns57.7256K
Qwen3.6 35B A3B36B (3B active)22.1 GBRuns158.5256K

RunsFits fully in VRAM; speed is estimated from VRAM bandwidth.

Needs RAM offloadMoE only: expert weights sit in system RAM, so speed is estimated from 70 GB/s RAM bandwidth.

Too bigWon’t fit on one card at this quantization, even with RAM offload.

Full calculation rules are on the Methodology page.

What LLMs can multiple CMP 170HX 40GB cards run?

Two CMP 170HX 40GB cards run gpt-oss 120B at 8-bit at about 133 tokens/s; large MoE needs four. Four PCIe 2.0 lanes per card make syncing slow.

ModelSizeCardsTotal priceTotal VRAMSpeed t/sTotal power
Qwen3.8 Flash Next176B (6B active)111.3 GB4 cards$11,736160 GB121.91,000 W
DeepSeek V4 Flash284B (13B active)155.1 GB8 cards$23,472320 GB93.42,000 W
Hy3295B (21B active)182.2 GB8 cards$23,472320 GB50.22,000 W
GLM 5.3 Flash320B (18B active)199.7 GB8 cards$23,472320 GB70.22,000 W

Full calculation rules are on the Methodology page.

Who it suits

Good fit

  1. You use only Linux, don't mind tinkering and want A100 generation speed

    It's as fast as the A100 40GB on the same model, about 65 tokens/s on Qwen3.8 27B at 4-bit

  2. You want 30B-class models at 8-bit

    Qwen3.8 27B at 8-bit (29 GB) fits and runs at about 39 tokens/s, which 24GB cards can't do

  3. You mainly run MoE models

    Qwen3.6 35B A3B and GLM 4.7 Flash run at about 156 to 159 tokens/s at 4-bit

Not a good fit

  1. You use Windows or don't want to touch the kernel

    The unlock patch supports only Linux and specific versions of the open-source driver, and you have to turn off Secure Boot

  2. You switch models often or need to run weights from system RAM

    PCIe is only Gen2 x4, so moving data between VRAM and RAM is slow

  3. You want a warranty and worry-free long-term use

    40GB is not an official spec, so there's no after-sales support once it's sold

Before you buy

  1. The 40GB is unlocked, not soldered on

    The “40GB” sellers advertise isn't the card's factory spec. The CMP 170HX ships with only 10GB enabled (another version has 8GB); the rest of the memory is actually inside the chip package, locked by firmware, and flashing the BIOS can't change that. Unlocking relies on the open-source tool cmpunlocker, which patches the driver to release the locked memory at boot, while also lifting the compute cap and raising PCIe to Gen2. So the patch lives in your computer's operating system and the card itself is unchanged: moving to another machine or reinstalling the OS means installing it again. In theory the 10GB version can be unlocked to 80GB, but the community reports that's unstable, so the tool uses the 40GB setting for 10GB cards.

  2. Linux only, with limited driver versions

    The patch has very specific system requirements: Linux x86-64, root access, and Secure Boot turned off (the modified driver module isn't signed). It accepts only a few nvidia-open driver versions on its list (currently the 610 and 615 series); if your installed version isn't on the list, the install script simply exits. You need to reinstall it after upgrading the kernel or driver. There's no such patch for Windows, where the card can only be used at its factory 10GB.

  3. Test the memory while you can still return it

    Unlocked memory isn't necessarily all good: Tom's Hardware warns that the locked portion may have been defective to begin with, and wccftech notes that some cards are only stable at a smaller capacity. When the card arrives, use a tool like cmp_memory_tester to fill and test all 40GB from start to finish while the return window is still open.

  4. The board is nearly identical to the A100's

    Taken apart, its circuit board is almost the same as the A100 40GB PCIe's, just with some components left unpopulated, so A100 water blocks fit directly (one user went with the Bykski N-TESLA-A100-X-V2). Like the A100, it takes power through one 8-pin CPU (EPS) connector, and the card has no fan and no video output.

Compared with similar GPUs

CMP 170HX 40GB vs A100 40GB PCIe, CMP 170HX 64GB, and GeForce RTX 4090: price, VRAM, bandwidth, compute and local LLM speed compared.

SpecCMP 170HX 40GBA100 40GB PCIeCMP 170HX 64GBGeForce RTX 4090
Memory
40 GB
40 GBSame
64 GB60% more
24 GB40% less
Bandwidth
1,560 GB/s
1,555 GB/sSame
1,493 GB/s4% lower
1,008 GB/s35% lower
BF16 / FP16 compute
202 TFLOPS
312 TFLOPS54% higher
202 TFLOPSSame
330 TFLOPS64% higher
INT8 compute
404 TOPS
624 TOPS54% higher
404 TOPSSame
661 TOPS64% higher
Qwen3.8 27B speed (2-bit)
101.9 t/s
101.6 t/sSame
98.1 t/s4% slower
69.3 t/s32% slower
Largest dense model (4-bit)
65B
65BSame
107B65% more
37B43% less
Power
250 W
250 WSame
250 WSame
450 W80% higher
GPU interconnect
Not supported
NVLink 600 GB/s
Not supported
Not supported
Interface
PCIe 2.0 x4
PCIe 4.0 x16
PCIe 2.0 x4
PCIe 4.0 x16
Released
2021-09
2020-06
2021-06
2022-10
eBay median

As an eBay Partner, VRAMGlass may be compensated if you buy through the eBay links on this page. The price you pay stays the same.

Other markets

Amazon.jp · Japan
N/A
No listings
View
Xianyu · Mainland China
$2,929
3 listings
View