AMD Radeon HD 8970M vs AMD Radeon RX 6700S Comparison

AMD
RADEON

AMD Radeon HD 8970M

CORE STATE Neptune
VRAM 4 GB
CLOCK SPEED 900 MHz
TDP 100 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2013
VS
AMD
RADEON

Radeon RX 6700S

CORE STATE Navi 23
VRAM 8 GB
CLOCK SPEED 2000 MHz
TDP 80 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

geekbench_opencl
21,237
70,965
3dmark_3dmark_steel_nomad_dx12
N/A
1,451
geekbench_metal
N/A
72,864
geekbench_vulkan
N/A
76,150
passmark_directx_10
N/A
87
passmark_directx_11
N/A
134
passmark_directx_12
N/A
58
passmark_directx_9
N/A
195
passmark_g2d
N/A
739
passmark_g3d
N/A
15,066
passmark_gpu_compute
N/A
5,990

Analysis: AMD Radeon HD 8970M vs AMD Radeon RX 6700S

# AMD Radeon RX 6700S vs AMD Radeon HD 8970M

The AMD Radeon RX 6700S and AMD Radeon HD 8970M represent two distant eras of mobile graphics, separated by nearly a decade of architectural evolution. The RX 6700S, built on RDNA 2.0 and targeting modern laptops, faces off against the GCN 1.0-based HD 8970M from the Solar System generation. Benchmark data shows a decisive generational gap, with the RX 6700S delivering a 234.2% advantage in the only shared test, yet the HD 8970M still holds its own in the percentile rankings, sitting just one point behind its modern counterpart.

Head-to-Head Benchmarks

The sole direct comparison available comes from Geekbench OpenCL, where the RX 6700S scores 70,965 points against the HD 8970M's 21,237 points. That translates to a 234.2% delta in favor of the newer card — more than triple the compute throughput. To put this in perspective, the RX 6700S's score places it in the 67th percentile of all GPUs, while the HD 8970M sits at the 66th percentile. The gap in raw compute is stark, yet the percentile difference is almost negligible, suggesting that both cards occupy similar relative positions in their respective eras.

Looking at the RX 6700S's broader benchmark suite, it posts a Passmark G3D score of 15,066 and a Passmark GPU Compute score of 5,990. Its average benchmark score across all tests is 22,154, which places it within 0.1% of the AMD Radeon RX 5700 (22,170) and 1.4% ahead of the NVIDIA GeForce GTX 1060 6 GB (21,856). The RX 6700S trails the NVIDIA GeForce RTX 5060 Mobile by 1.3% (22,435) and the AMD Radeon RX 7700 XT by 1.7% (22,549). These are tight margins, indicating that the RX 6700S punches well above its mobile positioning when compared to desktop and newer laptop parts.

The HD 8970M, with only its Geekbench OpenCL result available, shows an average score of 21,237. That figure is 0.4% above the AMD Radeon RX Vega M GL (21,153) and 1% above the NVIDIA GeForce RTX 5050 (21,035). It falls 0.7% short of the NVIDIA RTX A4000 Mobile (21,379) and 1.8% behind the NVIDIA Quadro RTX 5000 (21,629). For a 2013-era part, the HD 8970M's OpenCL showing remains remarkably competitive against much newer hardware, though it lacks the modern feature set to translate that compute into contemporary gaming performance.

Architecture Differences

The RX 6700S is built on the Navi 23 chip using TSMC's 7 nm process, packing 11,060 million transistors into a 237 mm² die. That yields a transistor density of 46.7 million per square millimeter. The HD 8970M, by contrast, uses the Neptune chip on a 28 nm process, with just 2,800 million transistors on a 212 mm² die — a density of 13.2 million per square millimeter. The architectural leap from GCN 1.0 to RDNA 2.0 is evident in every metric.

The RX 6700S features 1,792 shading units, 112 texture mapping units, and 64 raster output pipelines, alongside 28 dedicated ray tracing cores. The HD 8970M offers 1,280 shading units, 80 TMUs, and 32 ROPs, with no ray tracing hardware at all. Clock speeds tell a similar story: the RX 6700S runs at a 1700 MHz base and 2000 MHz boost, with a 1890 MHz game clock, while the HD 8970M operates at just 850 MHz base and 900 MHz boost.

Memory configurations diverge significantly. The RX 6700S uses 8 GB of GDDR6 on a 128-bit bus, delivering 224.0 GB/s of bandwidth at 14 Gbps effective. The HD 8970M relies on 4 GB of GDDR5 on a wider 256-bit bus, but its slower 4.8 Gbps effective speed yields only 153.6 GB/s. Despite the narrower bus, the RX 6700S achieves 45.8% more bandwidth thanks to faster memory technology.

Compute throughput is where the gap becomes overwhelming. The RX 6700S delivers 7.168 TFLOPS of FP32 performance, with 14.34 TFLOPS of FP16 (2:1 ratio). The HD 8970M manages just 2.304 TFLOPS FP32, with no FP16 support listed. Pixel fill rates are 128.0 GPixel/s versus 28.80 GPixel/s, and texture rates are 224.0 GTexel/s versus 72.00 GTexel/s.

API support also reflects the generational divide. The RX 6700S supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The HD 8970M tops out at DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The RX 6700S also uses PCIe 4.0 x8, while the HD 8970M is limited to PCIe 3.0 x16. Power efficiency favors the newer card: the RX 6700S carries an 80 W TDP despite its far higher performance, while the HD 8970M draws 100 W. The RX 6700S is an integrated GPU (IGP) with no power connectors, whereas the HD 8970M comes as an MXM module.

The Verdict

The data points to an unambiguous conclusion: the RX 6700S is the superior GPU by every measurable metric. Its 234.2% lead in Geekbench OpenCL is not a marginal improvement but a generational leap. The RX 6700S offers more than triple the FP32 throughput, nearly double the memory bandwidth, and four times the pixel fill rate of the HD 8970M. It adds ray tracing support, modern API compatibility, and does all of this while consuming 20 W less power.

However, the HD 8970M deserves context. Its 66th percentile ranking against all GPUs shows that, for its era, it was a high-end part. The fact that it remains within striking distance of much newer mobile GPUs in OpenCL compute — within 0.4% of the RX Vega M GL and 1% of the RTX 5050 — speaks to the longevity of GCN's compute architecture. But raw compute without modern features, higher clocks, or efficient memory cannot compensate for a near-decade of architectural progress.

For a modern laptop buyer, the RX 6700S is the obvious choice. It delivers competitive performance against parts like the RX 5700 and GTX 1060 6 GB, supports DirectX 12 Ultimate and ray tracing, and fits into thin-and-light designs with its 80 W TDP. The HD 8970M, by contrast, belongs in legacy systems. Its 4 GB GDDR5 frame buffer and lack of ray tracing hardware make it unsuitable for contemporary gaming workloads, despite its respectable compute showing. Anyone still running an HD 8970M should consider an upgrade; anyone choosing between these two should take the RX 6700S without hesitation.

Specification Differences

| Specification | AMD Radeon RX 6700S | AMD Radeon HD 8970M |

|---|---|---|

| Architecture | RDNA 2.0 | GCN 1.0 |

| Process Node | 7 nm | 28 nm |

| Transistors | 11,060 million | 2,800 million |

| Die Size | 237 mm² | 212 mm² |

| Transistor Density | 46.7M / mm² | 13.2M / mm² |

| Base Clock | 1700 MHz | 850 MHz |

| Boost Clock | 2000 MHz | 900 MHz |

| Game Clock | 1890 MHz | None |

| Memory Size | 8 GB | 4 GB |

| Memory Type | GDDR6 | GDDR5 |

| Memory Bus | 128 bit | 256 bit |

| Memory Speed | 14 Gbps effective | 4.8 Gbps effective |

| Memory Bandwidth | 224.0 GB/s | 153.6 GB/s |

| Shading Units | 1792 | 1280 |

| TMUs | 112 | 80 |

| ROPs | 64 | 32 |

| Ray Tracing Cores | 28 | None |

| Pixel Rate | 128.0 GPixel/s | 28.80 GPixel/s |

| Texture Rate | 224.0 GTexel/s | 72.00 GTexel/s |

| FP32 Performance | 7.168 TFLOPS | 2.304 TFLOPS |

| FP16 Performance | 14.34 TFLOPS (2:1) | None |

| TDP | 80 W | 100 W |

| Slot Width | IGP | MXM Module |

| Power Connectors | None | Not specified |

| Bus Interface | PCIe 4.0 x8 | PCIe 3.0 x16 |

| DirectX Support | 12 Ultimate (12_2) | 12 (11_1) |

| Vulkan Support | 1.4 | 1.2.170 |

| Release Date | 2022-01-03 | 2013-05-13 |

FAQ

Q: How much faster is the RX 6700S in the shared Geekbench OpenCL test?

A: The RX 6700S scores 70,965 points versus 21,237 for the HD 8970M, a 234.2% advantage.

Q: Which GPU has a higher percentile ranking among all GPUs?

A: The RX 6700S sits at the 67th percentile, while the HD 8970M sits at the 66th percentile — a difference of just one point.

Q: Does the HD 8970M support ray tracing?

A: No, the HD 8970M has no ray tracing cores. The RX 6700S includes 28 dedicated ray tracing cores.

Q: How do the power requirements compare between the two cards?

A: The RX 6700S has an 80 W TDP and requires no power connectors, while the HD 8970M has a 100 W TDP and comes as an MXM module.

Q: Which card offers higher memory bandwidth despite having a narrower bus?

A: The RX 6700S delivers 224.0 GB/s on a 128-bit bus, compared to the HD 8970M's 153.6 GB/s on a 256-bit bus, thanks to faster GDDR6 memory.

Q: How close is the HD 8970M to modern GPUs in compute performance?

A: The HD 8970M's average score of 21,237 is within 0.4% of the AMD Radeon RX Vega M GL (21,153) and 1% above the NVIDIA GeForce RTX 5050 (21,035).

DETAILED SPECIFICATIONS

SPECIFICATION
HD 8970M
RX 6700S
Core Specs
Shading Units
1,280
1,792 +40.0%
Shaders
1,280
1,792 +40.0%
TMUs
80
112 +40.0%
ROPs
32
64 +100.0%
Compute Units
20
28 +40.0%
Clocks
Base Clock
850 MHz
1700 MHz
Boost Clock
900 MHz
2000 MHz
Game Clock
—
1890 MHz
Memory Clock
1200 MHz 4.8 Gbps effective
1750 MHz 14 Gbps effective
Memory
Memory Size
4 GB
8 GB
VRAM (MB)
4,096
8,192 +100.0%
Memory Type
GDDR5
GDDR6
Memory Bus
256 bit
128 bit
Bandwidth
153.6 GB/s
224.0 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB per Array
L2 Cache
512 KB
2 MB
L3 Cache
—
32 MB
L0 Cache
—
32 KB per WGP
Performance
Pixel Rate
28.80 GPixel/s
128.0 GPixel/s
Texture Rate
72.00 GTexel/s
224.0 GTexel/s
FP32 (TFLOPS)
2.304 TFLOPS
7.168 TFLOPS
FP64 (TFLOPS)
144.0 GFLOPS (1:16)
448.0 GFLOPS (1:16)
FP16 (TFLOPS)
—
14.34 TFLOPS (2:1)
AI/RT
RT Cores
—
28
Power
TDP
100 W
80 W
TDP (W)
100
80 -20.0%
Power Connectors
—
None
Architecture
Architecture
GCN 1.0
RDNA 2.0
GPU Name
Neptune
Navi 23
Generation
Solar System (HD 8900M)
Navi Mobile (RX 6000M)
Process Size
28 nm
7 nm
Transistors
2,800 million
11,060 million
Die Size
212 mm²
237 mm²
Foundry
TSMC
TSMC
Density
13.2M / mm²
46.7M / mm²
API Support
DirectX
12 (11_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.4
OpenCL
2.1 (1.2)
2.1
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
MXM Module
IGP
Outputs
Portable Device Dependent
Portable Device Dependent
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x8
Other
Production
End-of-life
End-of-life
Predecessor
London
Polaris Mobile
Successor
Gem System
—
View Radeon HD 8970M Details View Radeon RX 6700S Details