Arc B580 vs Tesla M2090

Place in the ranking	548	135
Place by popularity	not in top-100	33
Cost-effectiveness evaluation	no data	91.92
Power efficiency	2.75	15.75
Architecture	Fermi 2.0 (2010−2014)	Xe2 (2024)
GPU code name	GF110	BMG-G21
Market segment	Workstation	Desktop
Release date	25 July 2011 (15 years ago)	13 December 2024 (1 year ago)
Launch price (MSRP)	no data	$249

Cost-effectiveness evaluation

The higher the ratio, the better. We use the manufacturer's recommended prices.

no data

Performance to price scatter graph

Currently popular graphics cards are shown for comparison.

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.

Pipelines / CUDA cores	512	2560
Core clock speed	651 MHz	2670 MHz
Boost clock speed	no data	2670 MHz
Number of transistors	3,000 million	19,600 million
Manufacturing process technology	40 nm	5 nm
Power consumption (TDP)	250 Watt	190 Watt
Texture fill rate	41.66	427.2
Floating-point processing power	1.332 TFLOPS	13.67 TFLOPS
ROPs	48	80
TMUs	64	160
Tensor Cores	no data	160
Ray Tracing Cores	no data	20
L1 Cache	1 MB	5 MB
L2 Cache	768 KB	18 MB

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 2.0 x16	PCIe 4.0 x8
Length	248 mm	272 mm
Width	2-slot	2-slot
Supplementary power connectors	1x 6-pin + 1x 8-pin	1x 8-pin

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR5	GDDR6
Maximum RAM amount	6 GB	12 GB
Memory bus width	384 Bit	192 Bit
Memory clock speed	924 MHz	2375 MHz
Memory bandwidth	177.4 GB/s	456.0 GB/s
Shared memory	-	-
Resizable BAR	-	+

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors	No outputs	1x HDMI 2.1a, 3x DisplayPort 2.1
HDMI	-	+

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 (11_0)	12 Ultimate (12_2)
Shader Model	5.1	6.6
OpenGL	4.6	4.6
OpenCL	1.1	3.0
Vulkan	N/A	1.4
CUDA	2.0	-
DLSS	-	+

Gaming performance

Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.

Average FPS across all PC games

Here are the average frames per second in a large set of popular games across different resolutions:

Full HD	27−30 −77.1%	118
1440p	14−16	63 +350%
4K	8−9 −79.5%	39

Cost per frame, $

1080p	no data	2.11
1440p	no data	3.95
4K	no data	6.38

FPS performance in popular games

Full HD
Low

Atomic Heart	206	206
Counter-Strike 2	210−220	210−220
Cyberpunk 2077	112	112
Resident Evil 4 Remake	177	177

Full HD
Medium

Atomic Heart	148	148
Battlefield 5	130−140	130−140
Counter-Strike 2	210−220	210−220
Cyberpunk 2077	97	97
Far Cry 5	173	173
Fortnite	160−170	160−170
Forza Horizon 4	150−160	150−160
PLAYERUNKNOWN'S BATTLEGROUNDS	150−160	150−160
Valorant	230−240	230−240

Full HD
High

Atomic Heart	101	101
Battlefield 5	130−140	130−140
Counter-Strike 2	210−220	210−220
Counter-Strike: Global Offensive	270−280	270−280
Cyberpunk 2077	82	82
Far Cry 5	160	160
Fortnite	160−170	160−170
Forza Horizon 4	150−160	150−160
Grand Theft Auto V	140	140
Metro Exodus	106	106
PLAYERUNKNOWN'S BATTLEGROUNDS	150−160	150−160
The Witcher 3: Wild Hunt	236	236
Valorant	230−240	230−240

Full HD
Ultra

Battlefield 5	130−140	130−140
Cyberpunk 2077	77	77
Far Cry 5	149	149
Forza Horizon 4	150−160	150−160
PLAYERUNKNOWN'S BATTLEGROUNDS	150−160	150−160
The Witcher 3: Wild Hunt	85	85
Valorant	230−240	230−240

Full HD
Epic

Fortnite

160−170

1440p
High

Counter-Strike 2	95−100	95−100
Counter-Strike: Global Offensive	270−280	270−280
Grand Theft Auto V	69	69
Metro Exodus	62	62
PLAYERUNKNOWN'S BATTLEGROUNDS	170−180	170−180
Valorant	260−270	260−270

1440p
Ultra

Battlefield 5	100−105	100−105
Cyberpunk 2077	56	56
Far Cry 5	110	110
Forza Horizon 4	110−120	110−120
The Witcher 3: Wild Hunt	68	68

1440p
Epic

Fortnite

100−110

4K
High

Atomic Heart	30−35	30−35
Counter-Strike 2	45−50	45−50
Grand Theft Auto V	78	78
Metro Exodus	46	46
The Witcher 3: Wild Hunt	84	84
Valorant	230−240	230−240

4K
Ultra

Battlefield 5	60−65	60−65
Counter-Strike 2	45−50	45−50
Cyberpunk 2077	30	30
Far Cry 5	59	59
Forza Horizon 4	70−75	70−75
PLAYERUNKNOWN'S BATTLEGROUNDS	50−55	50−55

4K
Epic

Fortnite

50−55

This is how Tesla M2090 and Arc B580 compete in popular games:

Arc B580 is 337% faster in 1080p
Arc B580 is 350% faster in 1440p
Arc B580 is 388% faster in 4K

All in all, in popular games:

there's a draw in 59 tests (100%)

Pros & cons summary

Performance score	8.84	38.53
Recency	25 July 2011	13 December 2024
Maximum RAM amount	6 GB	12 GB
Chip lithography	40 nm	5 nm
Power consumption (TDP)	250 Watt	190 Watt

Arc B580 has a 336% higher aggregate performance score, an age advantage of 13 years, a 100% higher maximum VRAM amount, a 88% more advanced lithography process, and 24% lower power consumption.

The Arc B580 is our recommended choice as it beats the Tesla M2090 in performance tests.

Be aware that Tesla M2090 is a workstation graphics card while Arc B580 is a desktop one.