RADEON

ATI Radeon HD 4670

AMD graphics card specifications and benchmark scores

512 MB
VRAM
MHz Boost
59W
TDP
128
Bus Width

At a Glance

AMD
VRAM 512 MB
Shaders 320
Bus Width 128-bit
TDP 59W
Memory Type GDDR3
Architecture TeraScale
nm
Process 55 nm
Released Sep 2008

ATI Radeon HD 4670 Specifications

ATI Radeon HD 4670 GPU Core

Shader units and compute resources

The ATI Radeon HD 4670 GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.

Shading Units
320
Shaders
320
TMUs
32
ROPs
8
Compute Units
4

ATI Radeon HD 4670 Clock Speeds

GPU and memory frequencies

Clock speeds directly impact the ATI Radeon HD 4670's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The ATI Radeon HD 4670 by AMD dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.

GPU Clock
750 MHz
Memory Clock
1000 MHz 2 Gbps effective
GDDR GDDR 6X 6X

AMD's ATI Radeon HD 4670 Memory

VRAM capacity and bandwidth

VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The ATI Radeon HD 4670's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.

Memory Size
512 MB
VRAM
512 MB
Memory Type
GDDR3
VRAM Type
GDDR3
Memory Bus
128 bit
Bus Width
128-bit
Bandwidth
32.00 GB/s

ATI Radeon HD 4670 by AMD Cache

On-chip cache hierarchy

On-chip cache provides ultra-fast data access for the ATI Radeon HD 4670, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.

L1 Cache
16 KB (per CU)
L2 Cache
128 KB

ATI Radeon HD 4670 Theoretical Performance

Compute and fill rates

Theoretical performance metrics provide a baseline for comparing the ATI Radeon HD 4670 against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.

FP32 (Float)
480.0 GFLOPS
Pixel Rate
6.000 GPixel/s
Texture Rate
24.00 GTexel/s

TeraScale Architecture & Process

Manufacturing and design details

The ATI Radeon HD 4670 is built on AMD's TeraScale architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the ATI Radeon HD 4670 will perform in GPU benchmarks compared to previous generations.

Architecture
TeraScale
GPU Name
RV730
Process Node
55 nm
Foundry
TSMC
Transistors
514 million
Die Size
146 mm²
Density
3.5M / mm²

AMD's ATI Radeon HD 4670 Power & Thermal

TDP and power requirements

Power specifications for the ATI Radeon HD 4670 determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the ATI Radeon HD 4670 to maintain boost clocks without throttling.

TDP
59 W
TDP
59W
Power Connectors
None
Suggested PSU
250 W

ATI Radeon HD 4670 by AMD Physical & Connectivity

Dimensions and outputs

Physical dimensions of the ATI Radeon HD 4670 are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.

Slot Width
Single-slot
Length
193 mm 7.6 inches
Bus Interface
PCIe 2.0 x16
Display Outputs
2x DVI1x S-Video
Display Outputs
2x DVI1x S-Video

AMD API Support

Graphics and compute APIs

API support determines which games and applications can fully utilize the ATI Radeon HD 4670. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.

DirectX
10.1 (10_1)
DirectX
10.1 (10_1)
OpenGL
3.3
OpenGL
3.3
OpenCL
1.1
Shader Model
4.1

ATI Radeon HD 4670 Product Information

Release and pricing details

The ATI Radeon HD 4670 is manufactured by AMD as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the ATI Radeon HD 4670 by AMD represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.

Manufacturer
AMD
Release Date
Sep 2008
Launch Price
67 USD
Production
End-of-life
Predecessor
Radeon R600
Successor
Evergreen

ATI Radeon HD 4670 Benchmark Scores

No benchmark data available for this GPU.

About ATI Radeon HD 4670

The ATI Radeon HD 4670 is a graphics card manufactured by AMD, built around the RV730 chip and the TeraScale architecture. It belongs to the Radeon R700 (HD 4600) generation and was released on 2008-09-09. The chip is fabricated by TSMC on a 55 nm process, integrating 514 million transistors on a die measuring 146 mm², for a transistor density of 3.5M per mm². The card is now end-of-life, with its predecessor being the Radeon R600 line and its successor being the Evergreen architecture. Its launch MSRP was 67 USD.

Benchmark Performance

The database records an average benchmark score of 0 for the ATI Radeon HD 4670, indicating that no aggregated performance measurement has been captured for this part. The percentileVsAllGpus field places the card at 50, meaning it sits exactly at the median of the entire GPU population tracked by the database. Half of all GPUs in the database outperform it, and half underperform it. This is the most informative comparative metric available, because the nearestRivals list is empty and no direct rival scores or deltas are provided.

The compute core of the HD 4670 is defined by 320 shading units, 32 texture mapping units, and 8 raster operation units. These resources produce a peak FP32 throughput of 480.0 GFLOPS. The pixel fill rate is 6.000 GPixel/s, and the texture fill rate is 24.00 GTexel/s. These three figures describe the card's raw processing limits. The pixel rate of 6.000 GPixel/s bounds how many pixels can be written per second in fill-rate-bound scenarios. The texture rate of 24.00 GTexel/s bounds how many texels can be sampled per second. The FP32 figure of 480.0 GFLOPS bounds general-purpose and shader compute workloads.

Taken together, these numbers describe a card deliberately balanced for mainstream use. The 55 nm process, the 514 million transistor count, and the 146 mm² die size all point to a mid-range chip. A transistor density of 3.5M per mm² is consistent with the era's manufacturing technology. The 59 W TDP and the absence of any power connectors mean the card draws all its power from the PCIe 2.0 x16 slot, and the suggested power supply is a modest 250 W.

Because the average benchmark score is 0, the percentile ranking of 50 is the only performance signal in the data. A median position implies that the HD 4670 was neither a performance outlier nor a bottom-tier part within the database's population. For applications that are within its fill-rate and compute limits, the card can be expected to perform adequately, but the data does not include frame-rate measurements to quantify this.

The DirectX 10.1 (10_1) and OpenGL 3.3 API support define the software boundary. Titles that require newer APIs are not supported, which constrains the card's practical performance envelope to older software.

Memory Subsystem

The HD 4670 ships with 512 MB of GDDR3 memory. The memory bus is 128 bits wide, and the memory clock is 1000 MHz, which yields an effective data rate of 2 Gbps per pin. The aggregate memory bandwidth is 32.00 GB/s.

This bandwidth figure is the key constraint for high-resolution workloads. At higher resolutions, the number of pixels and texture samples per frame increases, which raises the demand for memory bandwidth. With 32.00 GB/s, the HD 4670 can sustain a certain amount of data movement per second; beyond that, performance is limited by the memory subsystem rather than the compute units. The 128-bit bus width is the physical limit on data transferred per clock cycle, and the 1000 MHz clock determines how many cycles occur per second. The product of these two factors is the 32.00 GB/s figure.

The 512 MB frame buffer is another limiting factor. Large textures, high-resolution render targets, or multi-buffered scenes may exceed the available memory, forcing the card to spill to system memory over the PCIe 2.0 x16 bus. The display outputs — 2x DVI and 1x S-Video — support common monitors of the era, but the memory capacity and bandwidth are the practical limits for what can be displayed smoothly.

In the context of the card's overall performance, the memory subsystem is well matched to the compute resources. The 32.00 GB/s bandwidth can feed the 320 shading units and 32 TMUs at rates consistent with the 480.0 GFLOPS FP32 throughput and the 24.00 GTexel/s texture rate. A faster memory subsystem would likely be underutilized by the compute core, while a slower one would create a bottleneck. The 512 MB capacity is modest, however, and applications with large memory footprints may be constrained by capacity rather than bandwidth.

Who Should Consider It

The ATI Radeon HD 4670 is a card for users whose requirements align with its median performance position. The 50th percentile ranking means it is neither a high-end nor a low-end part in the database's GPU population. Users who need a card for basic graphical output, legacy software, or systems with limited power delivery may find it suitable.

The power profile is a strong indicator of the intended use case. With a TDP of 59 W, no power connectors, and a suggested power supply of 250 W, the card can be installed in systems with modest power supplies. The single-slot design and the 193 mm (7.6 inches) length ensure compatibility with most chassis. The PCIe 2.0 x16 interface is the connection standard.

For gaming, the card's 480.0 GFLOPS of FP32 compute, 6.000 GPixel/s pixel rate, and 24.00 GTexel/s texture rate suggest that it is best suited to lower resolutions and reduced detail settings. The 512 MB memory and 32.00 GB/s bandwidth are the relevant constraints for texture-heavy scenes. The DirectX 10.1 (10_1) support means that games written for DirectX 10.1 or earlier can run, while newer APIs are not supported.

Users who require multiple display outputs will find the 2x DVI and 1x S-Video configuration adequate for standard setups. The card's end-of-life status means it is no longer in production, so prospective users must source it from the used market. The release date of 2008-09-09 places it in a specific hardware generation, and its successor, Evergreen, is the architectural follow-up.

FAQ

Q: How much memory does the ATI Radeon HD 4670 have?

A: It has 512 MB of GDDR3 memory on a 128-bit bus, with a memory clock of 1000 MHz (2 Gbps effective) and 32.00 GB/s of bandwidth.

Q: What is the power consumption and power connector requirement?

A: The card has a TDP of 59 W, requires no power connectors, and has a suggested power supply of 250 W.

Q: What APIs are supported?

A: The card supports DirectX 10.1 (10_1) and OpenGL 3.3. Vulkan is not supported.

Q: What is the physical size of the card?

A: It is 193 mm (7.6 inches) long and has a single-slot design.

Q: When was the card released?

A: It was released on 2008-09-09 and is now end-of-life.

Q: What is the process technology?

A: The card is fabricated on a 55 nm process at TSMC, with 514 million transistors on a 146 mm² die, giving a transistor density of 3.5M per mm².

How It Compares

The nearestRivals list for the ATI Radeon HD 4670 is empty, so the database provides no direct rival names, scores, or delta percentages. Consequently, the card's comparative position must be derived from its percentile ranking and its generation context.

The percentileVsAllGpus value of 50 is the only quantitative comparison available. It places the card at the median of all GPUs in the database, meaning that half of the tracked GPUs perform better and half perform worse. This is a broad, population-level comparison rather than a head-to-head rival analysis.

Within its own product lineage, the HD 4670 sits between the Radeon R600 (its predecessor) and the Evergreen architecture (its successor). The Radeon R700 (HD 4600) generation is the immediate family. The card's 59 W TDP and lack of power connectors distinguish it from higher-power parts, but the database does not list any specific rivals to compare against.

The card's own specifications provide an internal benchmark of its capabilities. The 480.0 GFLOPS FP32 throughput, 6.000 GPixel/s pixel rate, 24.00 GTexel/s texture rate, and 32.00 GB/s memory bandwidth are the measurable limits of its performance. Without rival data, these figures, combined with the 50th percentile ranking, are the best available indicators of where the HD 4670 stands.

The NVIDIA Equivalent of ATI Radeon HD 4670

Looking for a similar graphics card from NVIDIA? The NVIDIA GeForce RTX 2080 offers comparable performance and features in the NVIDIA lineup.

NVIDIA GeForce RTX 2080

NVIDIA • 8 GB VRAM

View Specs Compare

Popular ATI Radeon HD 4670 Comparisons

See how the ATI Radeon HD 4670 stacks up against similar graphics cards from the same generation and competing brands.

Compare ATI Radeon HD 4670 with Other GPUs

Select another GPU to compare specifications and benchmarks side-by-side.

Browse GPUs