logo
Home Cases

Dell Pro Precision 9 T4 Review: 86 Xeon Cores and Two RTX PRO 6000 GPUs for Models Too Big for One Card

Certification
China Beijing Qianxing Jietong Technology Co., Ltd. certification
China Beijing Qianxing Jietong Technology Co., Ltd. certification
Customer Reviews
The sales staff of Beijing Qianxing Jietong Technology Co.,Ltd are very professional and patient. They can provide quotations quickly. The quality and packaging of the products are also very good. Our cooperation is very smooth.

—— 《Festfing DV》LLC

When I was looking for intel CPU and Toshiba SSD urgently, Sandy from Beijing Qianxing Jietong Technology Co., Ltd gave me a lot of help and got me the products I needed quickly. I really appreciate her.

—— Kitty Yen

Sandy of Beijing Qianxing Jietong Technology Co.,Ltd is a very careful salesman, who can remind me of configuration errors in time when I buy a server. The engineers are also very professional and can quickly complete the testing process.

—— Strelkin Mikhail Vladimirovich

We are very happy with our experience working with Beijing Qianxing Jietong. The product quality is excellent, and delivery is always on time. Their sales team is professional, patient, and very helpful with all our questions. We truly appreciate their support and look forward to a long-term partnership. Highly recommended!

—— Ahmad Navid

Quality: “Great experience with my supplier. The MikroTik RB3011 was already used, but it was in very good condition and everything works perfectly. Communication was fast and smooth, and all my concerns were addressed quickly. Very reliable supplier—highly recommended.”

—— Geran Colesio

I'm Online Chat Now

Dell Pro Precision 9 T4 Review: 86 Xeon Cores and Two RTX PRO 6000 GPUs for Models Too Big for One Card

November 17, 2026

The Dell Pro Precision 9 T4 is the flagship single-socket tower in Dell's Pro Precision line, and this review unit is configured for local AI at a scale most workstations cannot reach. It pairs an 86-core Intel Xeon 698X with 256GB of DDR5-6400 ECC memory, two 300W NVIDIA RTX PRO 6000 Blackwell Max-Q cards with 96GB of GDDR7 each, two 2TB Gen5 SSDs and a dual-port 25GbE adapter, drawing on a 2400W power supply. 


latest company case about Dell Pro Precision 9 T4 Review: 86 Xeon Cores and Two RTX PRO 6000 GPUs for Models Too Big for One Card  0


Key Takeaways


  • 1,A second GPU turns a model that does not fit on one card into a usable one. MiniMax M2.7 at 129.3GB generated 83.7 tokens/s for a single user when split across both cards, 2.8× the 30.3 tokens/s achieved with one card and the remainder of the model in system memory.
  • 2,The second GPU scaled serving by 1.85–2.02× and embedding by 1.92×. Peak llama.cpp output rose from 582.5 to 1,176.1 tokens/s on Ministral 3 3B and from 424.8 to 787.9 tokens/s on gpt-oss 120B with one server per GPU, while embedding one million Wikipedia passages fell from 890 to 464 seconds.
  • 3,A second GPU cut a LoRA epoch by 37%: one epoch on Ministral 3 8B took 31.5 minutes on one GPU and 19.7 minutes on two, ending at held-out losses of 1.169 and 1.167.Memory bandwidth is where the Xeon pulls ahead. STREAM Triad reached 328GB/s, 53% above the Threadripper PRO 9995WX in the Precision 7875, and the T4 finished the OpenFOAM drivAer solve in 293 seconds versus 556, and a 10-billion-digit y-cruncher run in 53.9 seconds versus 83.7.
  • 4,The Precision 7875 leads on core-bound CPU work: its 96-core Threadripper ran 37% ahead in 7-Zip and 30% ahead in Blender Monster, and finished the LLVM build in 43.7 seconds against 58.4.


Where the T4 Sits


Dell positions the T4 as its flagship single-socket tower workstation for organizations needing maximum compute density and expandability, with AI development, engineering simulation and scientific computing at the top of its workload list. It sits above the Pro Precision 9 T2, which uses the same Xeon 6 workstation platform in a smaller chassis with one GPU. The T4 adds the eight-channel processors at the top of the range, up to 86 cores, and room for up to four graphics cards depending on model.


Processor options start at the 12-core Xeon 634 and run through the 64-core Xeon 696X to the 86-core Xeon 698X in this unit, which carries 336MB of cache, a 2.0GHz base clock, a 4.8GHz maximum and a 350W rating. Memory scales to 4TB of DDR5 RDIMM across 16 slots, and this unit fills eight of them with 32GB modules at 6400MT/s. Graphics start at a single RTX A400, with card count tied to model: Dell's configurator lists four RTX A1000 cards, three RTX PRO 4000 Blackwell cards, two 300W RTX PRO 6000 Max-Q cards, or one 600W RTX PRO 6000.


The base configuration lists at $5,925. This build adds $8,300 for the Xeon 698X, $15,000 for 256GB of memory and $30,820 for the pair of RTX PRO 6000 Max-Q cards, before storage, networking and the 36-month ProSupport upgrade Dell automatically applies at this level.


Build, Design and Specifications


The T4 is a full tower at 449.8mm tall, 203.7mm wide and 617.5mm deep, listed at 24.1kg minimum and 33.6kg maximum depending on configuration. This unit uses the 2400W Platinum supply that Dell's configurator selects for the dual RTX PRO 6000 build, with a 1500W supply as the default on lighter configurations.


Serviceability is a strong point, beginning with tool-less entry through a side-panel latch and a 2400W power supply that slides out of the top rear by hand. Everything else, including graphics cards and SSDs, comes out with a Phillips screwdriver, and Dell's blue touch points mark the parts that release by hand. The lab found the platform easy to repair in the field, which matters at this price.


Cooling is the best execution we have seen from Dell in this class of tower. Air moves front to back, and large form-fitted cowls drive it down and across the processor and memory while keeping that channel separate from the PCIe area. This gives the two 300W cards an independent air stream so they are not drawing air heated by the 350W Xeon. Two fans sit between the processor zone and the card bay, and the fan assembly carries the same blue touch points and lifts out for memory access.


Expansion runs through six full-height PCIe slots: two Gen5 x16 that carry the GPUs, a Gen5 x8, a Gen4 x8, and two Gen4 slots with x8 connectors and x4 wiring. Storage covers three internal M.2 Gen5 slots and one Gen4 slot, two internal 3.5-inch SATA bays, and a front FlexBay holding up to four NVMe drives or two 3.5-inch drives alongside an optional slim optical drive. This unit boots from an internal 2TB Gen5 drive and carries a second 2TB Gen5 drive in another internal M.2 slot.


The front panel carries a headset jack, two 10Gbps USB-A ports, a 20Gbps USB-C port with PowerShare, a 10Gbps USB-C port and an optional SD card slot. The rear adds 10GbE and 1GbE RJ-45 ports, four 10Gbps USB-A ports, two 10Gbps USB-C ports, a 20Gbps USB-C port, serial, two PS/2 ports and line-out. This unit adds the Intel E810-XXV dual-port 25GbE SFP28 adapter, MediaTek Wi-Fi 7 MT7925 with Bluetooth 5.4, a media card reader and Dell's dual USB-C add-in card.


Security and management cover TPM 2.0, Dell SafeBIOS, chassis intrusion detection, self-encrypting drive support, BIOS secure erase and Intel vPro Enterprise. Dell lists the T4 at up to 85% recycled plastic in key components, 90% recycled aluminum in the handles and 11% recycled steel in the chassis, and the configuration is ENERGY STAR qualified.



Item Specification
Model Dell Pro Precision 9 T4 (PW9T4260)
Processor (as tested)

Intel Xeon 698X, 86 cores / 172 threads, 336MB cache, 2.0GHz base, up to 4.8GHz, 350W

Processor options Xeon 634 (12 cores) through Xeon 698X (86 cores)
Memory 256GB (8× 32GB) DDR5-6400 RDIMM ECC; 16 slots, up to 4TB
Graphics 2× NVIDIA RTX PRO 6000 Blackwell Max-Q, 96GB GDDR7 each, 300W each
Operating system Windows 11 Pro for Workstations (tested on Ubuntu 26.04.1 LTS)
Storage as configured 2× 2TB M.2 2280 Gen5 x4 TLC SED (both in internal M.2 slots)
Internal storage slots 3× M.2 2230/2280 Gen5 NVMe; 1× M.2 2230/2280 Gen4 NVMe; 2× 3.5-inch SATA
FlexBay Up to 4 NVMe drives plus optional slim ODD, or 2× 3.5-inch SATA
PCIe slots 2× Gen5 x16; 1× Gen5 x8; 1× Gen4 x8; 2× Gen4 x8 (x4 electrical)
Networking

Intel E810-XXV dual-port 25GbE SFP28 (add-in);

onboard 10GbE and 1GbE RJ-45; MediaTek Wi-Fi 7 MT7925, Bluetooth 5.4

Front ports

1× USB-C 20Gbps with PowerShare; 1× USB-C 10Gbps;

2× USB-A 10Gbps; headset jack; optional SD card slot

Rear ports

1× USB-C 20Gbps; 2× USB-C 10Gbps;

4× USB-A 10Gbps; serial; 2× PS/2; line-out

Power supply 2400W Platinum (1500W option)
Dimensions 449.8 × 203.7 × 617.5mm
Weight 24.1kg to 33.6kg by configuration
Security and management

TPM 2.0, Dell SafeBIOS, chassis intrusion detection,

self-encrypting drive support, BIOS secure erase, Intel vPro Enterprise

Sustainability

Up to 85% recycled plastic in key components, 90% recycled aluminum handles,

11% recycled steel chassis; ENERGY STAR qualified

Warranty ProSupport with on-site service after remote diagnosis, 36 months
Price $5,925 base; about $66,600 as configured 


Test Setup and Methodology

All four systems ran Ubuntu 26.04.1 LTS on kernel 7.0.0-43 with NVIDIA driver 595.99.02, CUDA 13, llama.cpp build b11716 and Ollama 0.40.3, on the Linux performance power profile. Results come from sr-client for local AI and client workloads, sr-harness for compile, compression, crypto, web serving and y-cruncher, and sr-suite r5.28 for GROMACS, OpenFOAM, ClickHouse, Valkey and memory bandwidth; each figure is the median of repeated passes. All systems ran with BIOS thermal mode set to Ultra Performance, with the T4 on BIOS 1.2.0.


Every comparison system is a Dell tower with RTX PRO 6000 Blackwell graphics. The Precision 7875 pairs the 96-core Threadripper PRO 9995WX with the same two Max-Q cards and 512GB of DDR5-5600, making it the closest match. The Pro Precision 9 T2 runs the 24-core Xeon 658X with one Max-Q card, and the Pro Max Tower T2 runs the 24-core Core Ultra 9 285K with the 600W RTX PRO 6000, showing what the higher power limit adds per GPU.


Local AI Performance


Every system here carries at least one RTX PRO 6000 Blackwell with 96GB of GDDR7, so single-GPU results measure the card, its power limit and how quickly the platform feeds it. The T4's two cards are what set it apart, and two-GPU tests run each model three ways where applicable: two independent servers, one per GPU, for throughput; one model split by layer across both cards; and, for MiniMax M2.7, one card with the rest of the model in system memory.


On one GPU the T4 lands where the 300W limit puts it. It generated 166.9 tokens/s for one user on gpt-oss 120B and peaked at 424.8 across 64 concurrent requests, within 1 to 9% of the Precision 7875's identical Max-Q card across all four models and level with the Pro Precision 9 T2. The 600W card in the Pro Max Tower T2 is 13 to 25% faster at peak on every model, reaching 520.7 tokens/s on gpt-oss 120B.


Running one server per GPU raised the T4's peak output by 1.85 to 2.02× across the four models: 582.5 to 1,176.1 tokens/s on Ministral 3 3B, 383.6 to 765.7 on the 8B model, and 158.1 to 310.8 on Qwen3.8 27B. gpt-oss 120B scaled 1.85× to 787.9 tokens/s on the T4 and 1.98× to 905.8 on the Precision 7875, peaking at 128 concurrent requests versus 64 for the T4.


Splitting gpt-oss 120B by layer across both cards is the slower way to use the second GPU when the model already fits on one: it served one user at 170.6 tokens/s, within 3% of a single card, and peaked at 539.2, 27% above one GPU but well short of the 787.9 that two replicas delivered. The split layout earns its place for models that do not fit on one card, which is where MiniMax M2.7 comes in.


MiniMax M2.7 is a 230-billion-parameter mixture-of-experts model, and this 4-bit quantization takes 129.3GB, more than the 96GB on one RTX PRO 6000. On one card with the remainder in system memory, the T4 generated 30.3 tokens/s for one user and took 16.2 seconds to return the first token. Split across both cards, single-user output rose to 83.7 tokens/s, 2.8× the one-card rate; time to first token fell from 16.2 to 3.1 seconds and peak throughput rose from 35.5 to 127.3 tokens/s.


The one-GPU numbers show how much the host platform matters once a model spills into system memory. The T4's eight channels of DDR5-6400 put it 34% ahead of the four-channel Pro Precision 9 T2 at 22.6 tokens/s and 1.9× ahead of the dual-channel Pro Max Tower T2 at 15.8, even though that system's 600W card is faster on every model that fits. The Precision 7875 edged the T4 at 32.8 tokens/s with 35% less memory bandwidth, so bandwidth alone does not explain the result; we report the 7875's lead as measured without isolating its cause.


Cold model loads favor the Gen5 drives: the T4 loaded gpt-oss:120b from its SK hynix Gen5 SSD in 15.2 seconds, matching the Pro Precision 9 T2 and well ahead of the 25.8 and 28.2 seconds on the Gen4-equipped Precision 7875 and Pro Max Tower T2. Warm loads from the page cache reverse that order, with the 7875 at 5.0 seconds against 7.5 on the T4, and loading a copy onto each GPU at once took 26.5 seconds on the T4.


RAG, Fine-Tuning and Generative AI


The RAG-at-scale test hides SQuAD questions among a million Wikipedia passages, embeds them with nomic-embed-text, builds an HNSW index and answers with Phi-4-mini. Two GPUs cut the T4's embedding time from 890 to 464 seconds, a 1.92× speedup, against 423 seconds for the Precision 7875; the 600W card in the Pro Max Tower T2 was the fastest single GPU at 722 seconds.


Index build and vector search run on the CPU, and that is where the T4 leads. It built the HNSW index in 27.3 seconds against 34.8 on the Precision 7875 and 118.6 on the Pro Max Tower T2, and searched at 98,503 queries/s at ef 64, 1.51× the 7875 and 5.6× the Core Ultra system. At ef 256 it held 32,149 queries/s with 97.6% recall against exact search, with answers returning in a median of 0.12 seconds.


The one-epoch LoRA test fine-tunes Ministral 3 8B in BF16 on Dolly 15k across 1,849 steps and scores 200 held-out examples every 100 steps. Every system started at a held-out loss of 1.534 and finished between 1.167 and 1.172, so the difference comes down to time per epoch. One T4 GPU finished in 31.5 minutes at 1,584 tokens/s, within 3% of the Pro Precision 9 T2 on the same Max-Q card; the Precision 7875 took 27.2 minutes and the 600W card in the Pro Max Tower T2 took 22.3 minutes. Adding the second GPU cut the T4's epoch to 19.7 minutes at 2,528 tokens/s, a 1.60× speedup that beat the single 600W card's 22.3 minutes, while the Precision 7875 completed its two-GPU epoch in 18.1 minutes, a 1.50× speedup.


Both cards run data-parallel with two examples per GPU and gradients accumulated to the same global batch of eight, so the two-GPU run sees the same examples at each step and lands on the same loss. With two short examples per GPU in each pass, the second card has little work to absorb and gradient exchange takes a larger share of each step. The epoch peaked at 19.5GiB of GPU memory on one card and 19.7GiB per card on two, a fraction of the 96GB available.


The T4 also passed every coding agent run at every model tier, including all three gpt-oss:20b runs at a 64K context where the other three systems passed two of three, and generated 161.5 tokens/s on gpt-oss:120b. Image generation runs on one GPU, so its 40.96 images/min on FLUX.2 klein in BF16 sits with the other Max-Q systems and behind the 600W card at 54.25.


CPU, Storage, Thermal and Service Results


The CPU results put the T4's 86 Xeon cores against the Precision 7875's 96 Threadripper cores, with the two 24-core T2s as reference points. The T4 leads where memory bandwidth decides the result, and the 7875 leads where core count and clocks do.


The T4 scored 619.8 GIPS in 7-Zip and 961.8 samples/min in Blender Monster, 2.2 and 2.4× the 24-core Pro Precision 9 T2, while the Precision 7875 ran 37% ahead in 7-Zip and 30% ahead in Blender, finished the LLVM build in 43.7 seconds against 58.4, and the Linux kernel allmodconfig build in 264 seconds against 312. Per-core speed is the T4's weak point, with the lowest one-thread 7-Zip score in this group at 8.85 GIPS.


HandBrake's x265 encode is the outlier here, and the cause is the encoder more than the processor: the other three systems all landed between 40.0 and 41.7fps with 24 or 96 cores, so x265 at this preset does not scale with core count, and the T4's 31.4fps is consistent with its lower per-core speed on the threads x265 uses. During the encode the T4 averaged about 1GHz across its 172 threads at 51°C to 64°C, showing most of the chip idle. SVT-AV1 scaled better, at 159.4fps on the T4 against 255.8 on the 7875.


Eight channels of DDR5-6400 give the T4 328GB/s in STREAM Triad, 53% above the Precision 7875's DDR5-5600 and 2.3× the four-channel Pro Precision 9 T2. Bandwidth-bound work follows: the T4 solved the 3-million-cell OpenFOAM drivAer case in 293 seconds against 556 on the 7875 and 826 on the Pro Precision 9 T2, while the Pro Max Tower T2 did not finish within the suite's 150-minute limit; the T4 also ran the 22.6-million-cell case in 6,851 seconds.


GROMACS benchPEP, the large all-core molecular dynamics case, ran at 1.243 ns/day on the T4 against 1.034 on the 7875, and the LU solve reached 1,660 GFLOPS against 1,172. y-cruncher computed 10 billion digits of Pi in 53.9 seconds against 83.7 and 25 billion in 155.6 seconds against 259.6. Dense compute that stays in cache favors the Threadripper, which led OpenBLAS DGEMM at 4,745 GFLOPS against 3,664.


ClickHouse ran the 43 ClickBench queries in 3.21 seconds hot and 6.45 seconds cold on the T4, 0.33 seconds behind the 7875 on the hot run and 0.64 seconds ahead on the cold run. Valkey favors fast cores over many cores, and the T4's 666,714 SET requests/s trail all three comparison systems, with the Core Ultra 9 285K leading at 1.72 million — a pattern that matches the T4's one-thread results and is worth weighing for latency-bound services. With all 172 threads loaded and the processor at an 87°C mean, the T4 searched 68.21 million nodes/s in Stockfish, 1.5× the 48-thread Pro Precision 9 T2 and well under half of the 7875's 168.27 on 192 threads.


The T4's 2TB SK hynix Gen5 boot drive delivered sequential reads of 14,152MB/s and writes of 10,078MB/s, roughly twice the Gen4 drives in the Precision 7875 and Pro Max Tower T2, with random performance peaking at 2.31 million read IOPS and 1.83 million write IOPS. The Pro Precision 9 T2's 20,914MB/s sequential read exceeds what one Gen5 x4 link carries, which fits that system's striped array of Samsung PM9E1 drives; here the boot drive was tested alone, without the second 2TB drive.


With the BIOS in Ultra Performance mode, the Xeon 698X peaked at 93°C in 7-Zip and 96°C in GROMACS, and clock figures are averages across all 172 logical CPUs. Blender and Stockfish load every thread and held 2.5GHz to 2.6GHz, above the 2.0GHz base. GROMACS and OpenBLAS load 64 and 86 physical cores and leave the remaining threads idle near 0.8GHz, which is why their averages read about 1.3GHz. GPU-led work kept the processor cooler, at a 61°C to 65°C mean during LLM serving, fine-tuning and RAG, since those tests lean on the cards.


Conclusion


The Dell Pro Precision 9 T4 is built for local AI work, and the second RTX PRO 6000 is where it shows. Two Max-Q cards raised peak serving throughput 1.85 to 2.02× across four models and embedding throughput 1.92×, cut a LoRA epoch on Ministral 3 8B from 31.5 to 19.7 minutes, and turned MiniMax M2.7 — a model too large for one card — from 30.3 to 83.7 tokens/s for a single user. On gpt-oss 120B, one server per GPU reached 7,091 total tokens/s at 64 requests, while splitting the model across both cards returned a single user's first token in 719ms against 1,189ms.


latest company case about Dell Pro Precision 9 T4 Review: 86 Xeon Cores and Two RTX PRO 6000 GPUs for Models Too Big for One Card  1


Eight channels of DDR5-6400 gave the Xeon 698X a 53% memory bandwidth lead over the Threadripper PRO 9995WX. That bandwidth carried the T4 to faster OpenFOAM, GROMACS benchPEP, y-cruncher and HNSW search results than the Precision 7875, and its Gen5 storage loaded large models faster. The chassis deserves credit as well, with the best cooling layout we have seen from Dell in this class and tool-less access to the power supply.


The 7875 remains ahead on core-bound rendering, compression and compile work by 18 to 38%, and by 60% in SVT-AV1. The Xeon's per-core speed trailed every system in this group, which showed in Valkey and other lightly threaded services. Fine-tuning on a single GPU was also slower on the T4, where the LoRA epoch took 31.5 minutes against 27.2 on the 7875 and 22.3 on the 600W card in the Pro Max Tower T2, with every system finishing within 0.005 of the same held-out loss.


At about $66,600 as configured , the T4 suits teams that want to serve, embed and fine-tune models on-premises — including models needing more than 96GB of GPU memory — alongside memory-bound simulation and analytics on the same machine. Buyers whose work is mostly rendering and compilation will find the Threadripper platform faster, and buyers who need one GPU can get the same card in the smaller Pro Precision 9 T2.


Beijing Qianxing Jietong Technology Co., Ltd.
Sandy Yang/Global Strategy Director
WhatsApp / WeChat: +86 13426366826
Email: yangyd@qianxingdata.com
Website: www.qianxingdata.com/www.storagesserver.com
Business Focus:
ICT Product Distribution/System Integration & Services/Infrastructure Solutions
With 20+ years of IT distribution experience, we partner with leading global brands to deliver reliable products and professional services.
“Using Technology to Build an Intelligent World”Your Trusted ICT Product Service Provider!

Contact Details
Beijing Qianxing Jietong Technology Co., Ltd.

Contact Person: Ms. Sandy Yang

Tel: 13426366826

Send your inquiry directly to us (0 / 3000)