AMD Radeon R7 M350 vs NVIDIA GeForce GTX 770M Comparison

The Verdict

For two mobile GPUs from the same era, the data draws a clear line: the NVIDIA GeForce GTX 770M is the stronger performer, winning the only head-to-head benchmark by a significant margin. If you are choosing between these two based strictly on the numbers, the GTX 770M is the pick for anyone who wants more compute throughput. The AMD Radeon R7 M350, however, is not without its own merits — it posts a higher score in a different benchmark API, and it offers more memory capacity.

The GTX 770M takes the Geekbench OpenCL test with a score of 8552, beating the R7 M350's 6991 by 18.3%. That is a decisive win, not a marginal one. The data also shows the GTX 770M has a higher average benchmark score (6000 vs 6327 for the R7 M350), but note that this average is pulled down by its additional Metal benchmark result of 3448, which the AMD card does not have. Looking at raw specification advantages, the GTX 770M has more than double the shading units (960 vs 384), more than triple the texture mapping units (80 vs 24), and triple the ROPs (24 vs 8).

The R7 M350's only benchmark victory is in Geekbench Vulkan, where it scores 5662; the GTX 770M has no Vulkan result to compare. So if your workload leans on Vulkan, the AMD card has data backing it, but for general compute and OpenCL, the NVIDIA part is the clear winner. The Verdict: pick the GTX 770M for raw performance and higher memory bandwidth; pick the R7 M350 only if you specifically need 4 GB of VRAM or Vulkan-optimized compute, as its 3 GB GDDR5 counterpart cannot match that capacity.

Architecture Differences

The two GPUs come from different architectural families, and the data shows distinct design philosophies. The AMD Radeon R7 M350 uses the GCN 3.0 architecture on a chip codenamed Meso, fabricated on a 28 nm process at TSMC. It packs 1,550 million transistors onto a 125 mm² die, giving it a transistor density of 12.4 million per square millimeter. The NVIDIA GeForce GTX 770M uses the older Kepler architecture on the GK106 chip, also built on TSMC's 28 nm node, but with a much larger 221 mm² die and 2,540 million transistors — that is a density of 11.5 million per square millimeter.

The transistor counts tell a story: NVIDIA spent its budget on more execution units, while AMD concentrated on a smaller, denser chip. The GTX 770M's 960 shading units, 80 TMUs, and 24 ROPs dwarf the R7 M350's 384 shading units, 24 TMUs, and 8 ROPs. This explains the large performance gap in the benchmark data. Clock speeds differ as well: the R7 M350 runs at a 1000 MHz base and 1015 MHz boost, while the GTX 770M runs at 706 MHz base and 797 MHz boost. Despite the lower clocks, the GTX 770M's massive execution resource advantage wins out.

Memory architecture is another major split. The R7 M350 uses 4 GB of DDR3 on a 64-bit bus, yielding 16.00 GB/s of bandwidth. The GTX 770M uses 3 GB of GDDR5 on a 192-bit bus, delivering 96.19 GB/s — six times the bandwidth. The R7 M350's memory clock is listed as 1000 MHz with 2 Gbps effective, while the GTX 770M's is 1002 MHz with 4 Gbps effective. That bandwidth disparity is critical for memory-intensive tasks. API support also differs: the R7 M350 supports DirectX 12 (12_0) and Vulkan 1.2.170, while the GTX 770M supports DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6. The GTX 770M has a listed TDP of 75 W, while the R7 M350 has no TDP listed in the data.

Head-to-Head Benchmarks

The only direct head-to-head benchmark result in the data is Geekbench OpenCL, and it is not close. The NVIDIA GeForce GTX 770M scores 8552, while the AMD Radeon R7 M350 scores 6991. That is an 18.3% delta in favor of NVIDIA. In practical terms, this means the GTX 770M delivers roughly one-fifth more OpenCL compute throughput than the R7 M350 — a substantial gap that will show up in GPU-accelerated workloads like rendering, video encoding, and scientific compute.

The R7 M350 does have its own Geekbench Vulkan score of 5662, but the GTX 770M has no Vulkan result in the data, so a direct comparison is impossible. The GTX 770M also has a Geekbench Metal score of 3448, which the R7 M350 does not have. When looking at average benchmark scores, the R7 M350 posts 6327 versus the GTX 770M's 6000. However, this average includes the GTX 770M's lower Metal score, which drags its average down. The OpenCL head-to-head remains the most apples-to-apples comparison, and it favors the GTX 770M decisively.

Looking at the nearest rivals for context, the R7 M350's average score of 6327 places it right next to the AMD Radeon Pro WX 4100 (6330, 0% delta) and slightly above the NVIDIA Quadro K620 (6282, 0.7% delta). The GTX 770M's average of 6000 sits level with the AMD Radeon RX 6400 (6001, 0% delta) and just above the NVIDIA RTX PRO 6000 Blackwell Server (5996, 0.1% delta). These rival comparisons show both cards are in the same general performance tier, but the head-to-head OpenCL result separates them clearly.

Specification Differences

The two cards differ on nearly every major specification. Here is the breakdown:

• Shading Units: R7 M350 has 384; GTX 770M has 960.
• Texture Mapping Units: R7 M350 has 24; GTX 770M has 80.
• Render Output Units: R7 M350 has 8; GTX 770M has 24.
• Base Clock: R7 M350 runs at 1000 MHz; GTX 770M runs at 706 MHz.
• Boost Clock: R7 M350 boosts to 1015 MHz; GTX 770M boosts to 797 MHz.
• Memory Size: R7 M350 has 4 GB; GTX 770M has 3 GB.
• Memory Type: R7 M350 uses DDR3; GTX 770M uses GDDR5.
• Memory Bus Width: R7 M350 has a 64-bit bus; GTX 770M has a 192-bit bus.
• Memory Bandwidth: R7 M350 delivers 16.00 GB/s; GTX 770M delivers 96.19 GB/s.
• Memory Clock: R7 M350 runs at 1000 MHz (2 Gbps effective); GTX 770M runs at 1002 MHz (4 Gbps effective).
• Transistors: R7 M350 has 1,550 million; GTX 770M has 2,540 million.
• Die Size: R7 M350 is 125 mm²; GTX 770M is 221 mm².
• Transistor Density: R7 M350 has 12.4M / mm²; GTX 770M has 11.5M / mm².
• Pixel Rate: R7 M350 is 8.120 GPixel/s; GTX 770M is 15.94 GPixel/s.
• Texture Rate: R7 M350 is 24.36 GTexel/s; GTX 770M is 63.76 GTexel/s.
• FP32 Performance: R7 M350 is 779.5 GFLOPS; GTX 770M is 1.530 TFLOPS.
• FP16 Performance: R7 M350 is 779.5 GFLOPS (1:1); GTX 770M has no FP16 data.
• TDP: GTX 770M is listed at 75 W; R7 M350 has no TDP listed.
• Bus Interface: R7 M350 uses PCIe 3.0 x8; GTX 770M uses MXM-B (3.0).
• Slot Width: GTX 770M is an MXM Module; R7 M350 has no slot width listed.
• Power Connectors: GTX 770M has none; R7 M350 has none listed.
• Display Outputs: GTX 770M is "Portable Device Dependent"; R7 M350 has none listed.
• DirectX Support: R7 M350 supports 12 (12_0); GTX 770M supports 12 (11_0).
• Vulkan Support: R7 M350 supports 1.2.170; GTX 770M supports 1.2.175.
• Release Date: R7 M350 released 2015-05-04; GTX 770M released 2013-05-29.
• Production Status: Both are end-of-life.

FAQ

Q: Which GPU is faster in OpenCL compute?

A: The NVIDIA GeForce GTX 770M wins the Geekbench OpenCL head-to-head with a score of 8552 versus the AMD Radeon R7 M350's 6991, an 18.3% advantage.

Q: Does the AMD card win any benchmark?

A: Yes, the R7 M350 scores 5662 in Geekbench Vulkan, while the GTX 770M has no Vulkan result listed — so it wins by default in that API.

Q: Which card has more memory bandwidth?

A: The GTX 770M has 96.19 GB/s of bandwidth from its GDDR5 memory on a 192-bit bus, while the R7 M350 has only 16.00 GB/s from DDR3 on a 64-bit bus.

Q: Why does the GTX 770M have a lower average benchmark score despite winning the head-to-head?

A: The GTX 770M's average of 6000 includes its Geekbench Metal score of 3448, which is much lower than its OpenCL score of 8552. The R7 M350's average of 6327 only includes its OpenCL and Vulkan scores.

Q: Which card has higher clock speeds?

A: The R7 M350 runs at 1000 MHz base and 1015 MHz boost, notably higher than the GTX 770M's 706 MHz base and 797 MHz boost.

Q: Is there a DirectX version difference?

A: Yes, the R7 M350 supports DirectX 12 (12_0), while the GTX 770M supports DirectX 12 (11_0), indicating a more complete feature set on the AMD side.

Where Each One Wins

The NVIDIA GeForce GTX 770M wins in raw compute performance. Its OpenCL score of 8552 beats the R7 M350's 6991 by 18.3%. It also has superior specifications across the board for throughput: 960 shading units versus 384, 80 TMUs versus 24, 24 ROPs versus 8, and 1.530 TFLOPS of FP32 performance versus 779.5 GFLOPS. The 96.19 GB/s memory bandwidth versus 16.00 GB/s makes it the clear choice for bandwidth-hungry tasks. Its higher pixel rate (15.94 GPixel/s versus 8.120 GPixel/s) and texture rate (63.76 GTexel/s versus 24.36 GTexel/s) reinforce this. For any OpenCL-based workload — rendering, video processing, or general GPU compute — the GTX 770M is the one to pick.

The AMD Radeon R7 M350 wins in a few specific areas. It has more memory capacity at 4 GB versus 3 GB, which matters for workloads that need to hold larger datasets in VRAM. It supports DirectX 12 (12_0) versus the GTX 770M's 12 (11_0), giving it a more modern feature set for DX12 titles. It also has a Vulkan score of 5662, and while the GTX 770M has no Vulkan result to compare, the data shows Vulkan is a functional API on this card. Its higher clock speeds (1000 MHz base versus 706 MHz base) and higher transistor density (12.4M / mm² versus 11.5M / mm²) show a more efficient design on a smaller die. The R7 M350 also has a slightly higher average benchmark score (6327 versus 6000), though this is skewed by the GTX 770M's lower Metal score.

In summary: the GTX 770M is the performance king for OpenCL and memory bandwidth, while the R7 M350 offers more VRAM, better DirectX 12 support, and a viable Vulkan path. Choose based on your workload's API and memory requirements.