Products · Dell · Workstation

Dell Precision 7960 Rack Workstation

Chips: 8 GPU options, from NVIDIA T400 to NVIDIA RTX 6000 Ada Generation
VRAM: 4, 16, 20, 24, 32, 40 or 48 GB
Released: 2024

Product page (opens in a new tab) Full AI report

Configurations

Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.

Configuration	Memory	Usable for AI	Bandwidth	LLMs that run well	Launch price
NVIDIA T400	4.0 GB	4.0 GB	80 GB/s	215 of 622	—
NVIDIA RTX 2000 Ada Generation	16.0 GB	16.0 GB	224 GB/s	455 of 622	—
NVIDIA RTX A4000	16.0 GB	16.0 GB	448 GB/s	460 of 622	—
NVIDIA RTX 4000 Ada Generation	20.0 GB	20.0 GB	360 GB/s	461 of 622	—
NVIDIA RTX 4500 Ada Generation	24.0 GB	24.0 GB	432 GB/s	466 of 622	—
NVIDIA RTX 5000 Ada Generation	32.0 GB	32.0 GB	576 GB/s	489 of 622	—
NVIDIA A800 40GB Active	40.0 GB	40.0 GB	1,555 GB/s	511 of 622	—
NVIDIA RTX 6000 Ada Generation	48.0 GB	48.0 GB	960 GB/s	517 of 622	—

Specifications 24.0 GB configuration

Maker	Dell
Type	Workstation
Chip	NVIDIA RTX 4500 Ada Generation
Video memory (VRAM)	24.0 GB
Usable for AI models	24.0 GB
Memory bandwidth	432 GB/s
FP16 compute	39.6 TFLOPS
Notes	Workstation with NVIDIA RTX professional graphics; each option below is a GPU you can configure. Listed on the NVIDIA Marketplace.
Product page	www.dell.com (opens in a new tab)

Best LLMs for the Dell Precision 7960 Rack Workstation 24.0 GB

Quality	Model	Quant	Memory	Speed	Runs
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 26B-A4BGoogle	`Q6_K`	23.4 GB	71.8 tok/s	Runs welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 35B-A3BAlibaba	`Q4_K_M`	23.9 GB	111 tok/s	Runs welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM-V 4.7 35B-A3BOpenBMB	`Q4_K_M`	23.4 GB	111 tok/s	Runs welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 35B-A3BAlibaba	`Q4_K_M`	23.9 GB	111 tok/s	Runs welltight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Nex N2 Mini (35B-A3B)Nex-AGI	`Q4_K_M`	23.4 GB	111 tok/s	Runs welltight fit
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	KAT-Coder V2.5 Dev (35B-A3B)Kuaishou	`Q4_K_M`	23.1 GB	111 tok/s	Runs welltight fit
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Sage-A1.5 35B-A3BInternScience	`Q4_K_M`	23.9 GB	111 tok/s	Runs welltight fit
83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Raon-1 mini Preview (30B-A4B)KRAFTON	`Q4_K_M`	19.4 GB	87.2 tok/s	Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Ornith 1.5 35B-A3BDeepReinforce	`Q4_K_M`	23.9 GB	111 tok/s	Runs welltight fit
84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Apodex 1.1 Mini (35B-A3B)Apodex	`Q4_K_M`	23.9 GB	111 tok/s	Runs welltight fit

Best Image models for the Dell Precision 7960 Rack Workstation 24.0 GB

Quality	Model	Quant	Memory	Speed	Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	Krea 2 TurboKrea	`FP8`	20.2 GB	6.7 s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE-Image TurboBaidu	`Q8 GGUF`	15.0 GB	6.4 s	Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 9BBlack Forest Labs	`FP8`	19.9 GB	2.8 s	Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`FP8`	12.4 GB	8.9 s	Runs great
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`FP16`	18.1 GB	1.7 s	Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`Q8 GGUF`	13.0 GB	5.0 s	Runs great

Best Video models for the Dell Precision 7960 Rack Workstation 24.0 GB

Quality	Model	Quant	Memory	Speed	Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2.5 (22B, video + audio)Lightricks	`FP8`	19.7 GB	3.1 min	Runs greatCPU offload
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Bernini-R A14B (video generation + editing)ByteDance	`FP8`	20.3 GB	19.7 min	Slowencoder in RAM
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP16`	17.5 GB	43 s	Runs great
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5B I2VZhipu AI	`FP8`	14.9 GB	4.7 min	Runs well
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	FramePack I2V (HunyuanVideo 13B)lllyasviel	`FP8`	19.6 GB	10.9 min	Runs wellencoder in RAM

Best Decision models for the Dell Precision 7960 Rack Workstation 24.0 GB

Quality	Model	Quant	Memory	Speed	Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 4BAlibaba	`Q8_0`	6.4 GB	91 ms	Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	zerank-2ZeroEntropy	`Q8_0`	6.4 GB	91 ms	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`F16`	3.2 GB	20 ms	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Shieldstral 1.0 3BMistral AI	`Q8_0`	6.1 GB	87 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Intern-Decision 4BShanghai AI Lab	`F16`	10.9 GB	81 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`F16`	3.2 GB	20 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	d1 3BLiquid AI	`F16`	8.1 GB	57 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	mxbai-rerank-large v2Mixedbread	`F16`	4.9 GB	44 ms	Runs great

Other products with the NVIDIA RTX 4500 Ada Generation

APEXX T4 PRO-XBOXX · Workstation · 4, 8, 16, 24, 32, 48 or 96 GBProduct page (opens in a new tab)
APEXX W4BOXX · Workstation · 4, 8, 16, 24, 32, 48 or 96 GBProduct page (opens in a new tab)
Precision 5860 Tower WorkstationDell · Workstation · 4, 8, 12, 16, 20, 24, 32, 40 or 48 GBProduct page (opens in a new tab)
Precision 7875 Tower WorkstationDell · Workstation · 4, 8, 12, 16, 20, 24, 32, 40 or 48 GBProduct page (opens in a new tab)
Precision 7960 Tower WorkstationDell · Workstation · 4, 8, 12, 16, 20, 24, 32, 40 or 48 GBProduct page (opens in a new tab)
ThinkStation P8 WorkstationLenovo · Workstation · 4, 8, 16, 20, 24, 32 or 48 GBProduct page (opens in a new tab)
Valence Workstation - VWS-172109266Exxact · Workstation · 4, 8, 20, 24, 32, 40, 48 or 96 GBProduct page (opens in a new tab)
TensorEX Rackmount Workstation - TWS-154715021Exxact · Workstation · 4, 8, 20, 24, 32, 40, 48, 94 or 96 GBProduct page (opens in a new tab)
TensorEX Rackmount Workstation - TWS-123065716Exxact · Workstation · 16, 20, 24, 32, 48, 72 or 96 GBProduct page (opens in a new tab)
TensorEX Rackmount Workstation - TWS-192623777Exxact · Workstation · 16, 20, 24, 32, 48, 72 or 96 GBProduct page (opens in a new tab)
Valence Workstation - VWS-135223847Exxact · Workstation · 20, 24, 32, 48, 72 or 96 GBProduct page (opens in a new tab)
Valence Workstation - VWS-173807702Exxact · Workstation · 4, 8, 20, 24, 32, 40, 48, 72 or 96 GBProduct page (opens in a new tab)

Spec sources

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.