Dell Precision 7875 Tower (RTX 4090)

Windows · Linux

Precision 7875 tower with NVIDIA GeForce RTX 4090, 64GB RAM (representative CTO).

From

$5,499

You'll be taken to Dell to complete your purchase.

Buy on Dell

Memory

24 GB

GPUs

1×

RAM

64 GB

Models

Type

Desktop

Inference Memory

24 GB

Accelerator

24 GB GDDR6X

System RAM

64 GB

CPU

AMD Threadripper PRO 7955WX

Windows, Linux

What it can run

58 models


all-MiniLM-L6-v2	FP16	–	Excellent
Arcee Trinity Mini 26B	Q5_K_M	62 tok/s	Excellent
Arcee Trinity Nano 6B	Q8_0	178 tok/s	Excellent
Code Llama 34B Instruct	Q4_K_M	22 tok/s	Good
Codestral 22B	Q5_K_M	35 tok/s	Excellent
DeepSeek Coder V2 Lite 16B	Q5_K_M	55 tok/s	Excellent
DeepSeek R1	Q2_K	1 tok/s	Not viable
DeepSeek R1 Distill Qwen 32B	Q4_K_M	24 tok/s	Good
DeepSeek R1 Distill Qwen 7B	Q4_K_M	92 tok/s	Excellent
DeepSeek V3	Q2_K	–	Not viable
FLUX.1 Dev	FP16	–	Excellent
Gemma 2 27B Instruct	Q4_K_M	22 tok/s	Good
Gemma 2 9B Instruct	Q8_0	80 tok/s	Excellent
Gemma 3 12B	Q5_K_M	75 tok/s	Excellent
Gemma 3 27B	Q4_K_M	22 tok/s	Good
Gemma 4 26B-A4B	Q5_K_M	229 tok/s	Excellent
Gemma 4 31B	Q4_K_M	38 tok/s	Good
Gemma 4 E2B	Q8_0	152 tok/s	Excellent
Gemma 4 E4B	Q8_0	94 tok/s	Excellent
GigaChat Lightning 10B	Q8_0	110 tok/s	Good
InternLM 2.5 7B Chat	Q8_0	88 tok/s	Excellent
Llama 3.1 70B Instruct	Q3_K_M	5 tok/s	Marginal
Llama 3.1 8B Instruct	Q8_0	95 tok/s	Excellent
Llama 3.2 11B Vision	Q8_0	95 tok/s	Excellent
Llama 3.2 1B Instruct	Q8_0	250 tok/s	Excellent
Llama 3.2 3B Instruct	Q8_0	170 tok/s	Excellent
Llama 3.3 70B Instruct	Q3_K_M	6 tok/s	Marginal
LLaVA 1.6 13B	Q5_K_M	30 tok/s	Good
Mistral 7B Instruct v0.3	Q8_0	90 tok/s	Excellent
Mistral Large 2 123B	Q2_K	3 tok/s	Marginal
Mistral Small 24B Instruct	Q5_K_M	32 tok/s	Good
Mixtral 8x7B Instruct	Q3_K_M	35 tok/s	Good
nomic-embed-text v1.5	FP16	–	Excellent
NVIDIA Nemotron-3-super-120B-A12B	Q2_K	18 tok/s	Marginal
Phi-3 Medium 14B Instruct	Q8_0	55 tok/s	Excellent
Phi-3 Mini 3.8B Instruct	Q8_0	130 tok/s	Excellent
Phi-4 14B	Q5_K_M	58 tok/s	Excellent
Phi-4 Mini	Q8_0	160 tok/s	Excellent
Qwen 2.5 14B Instruct	Q5_K_M	55 tok/s	Excellent
Qwen 2.5 7B Instruct	Q8_0	88 tok/s	Excellent
Qwen 2.5 Coder 32B Instruct	Q4_K_M	25 tok/s	Good
Qwen 2.5 Coder 7B Instruct	Q8_0	90 tok/s	Excellent
Qwen3-14B Instruct	Q8_0	41 tok/s	Good
Qwen3-30B-A3B	Q5_K_M	25 tok/s	Good
Qwen3-32B Instruct	Q4_K_M	30 tok/s	Good
Qwen3-32B Instruct	Q5_K_M	25 tok/s	Good
Qwen3-8B Instruct	Q8_0	83 tok/s	Excellent
Qwen3.5-122B-A10B	Q3_K_M	19 tok/s	Marginal
Qwen3.5-27B	Q5_K_M	40 tok/s	Good
Qwen3.5-397B (MoE)	Q2_K	–	Not viable
Qwen3.6-27B	Q5_K_M	40 tok/s	Good
Qwen3.6-35B-A3B	Q4_K_M	25 tok/s	Good
QwQ 32B Preview	Q4_K_M	24 tok/s	Good
Stable Diffusion 3 Medium	FP16	–	Excellent
Stable Diffusion 3.5 Large	FP16	–	Excellent
Stable Diffusion XL 1.0	FP16	–	Excellent
StarCoder 2 15B	Q8_0	50 tok/s	Excellent
Whisper Large V3	FP16	–	Excellent
Whisper Large V3 Turbo	FP16	–	Excellent

Showing 59 of 59 entries

Best Fit

Who this machine makes sense for

This machine is aimed at team, lab, or enterprise buyers who want a supported system instead of assembling a tower. 24 GB makes it viable for serious local workloads without a DIY build process.

Before You Buy

What to verify first

The main question is not whether the machine works, but whether the price premium is justified by warranty, support, and deployment simplicity versus an equivalent custom build.

All machines