AMD Radeon RX 9060 8GB Specs, Benchmarks & Pricing

The AMD Radeon RX 9060 is an entry-level RDNA 4 graphics card released on August 5, 2025, initially available only through OEM pre-built systems. Based on the Navi 44 XL GPU die (same die as the RX 9060 XT), it operates with 28 compute units and 1,792 stream processors, trimmed down from the 9060 XT's 32 CUs. The card features 56 2nd-generation AI Accelerators, 28 3rd-generation Ray Tracing accelerators, and 32 MB of Infinity Cache. With 8 GB of GDDR6 memory running at 18 Gbps on a 128-bit interface, it delivers 288 GB/s of memory bandwidth, slightly lower than the 9060 XT's 320 GB/s. The boost clock reaches 2,990 MHz with a game clock of 2,400 MHz, and the total board power is a modest 132W. The card is built on TSMC's 4nm (N4P) process with 29.7 billion transistors on a 199 mm2 die. It delivers 21.4 TFLOPS of FP32 compute and 172 TOPS of dense INT8 AI performance through RDNA 4's AI Accelerators. The RX 9060 supports PCIe 5.0 x16 and features DisplayPort 2.1a and HDMI 2.1b outputs. AMD positioned it to compete with NVIDIA's RTX 5050 in the OEM market, with performance approximately 13-14% below the RX 9060 XT 8GB. FSR 4 (FidelityFX Super Resolution 4), AMD's machine-learning upscaling technology exclusive to RDNA 4, is supported.

  • Release Date: August 5, 2025
  • GPU Architecture: RDNA 4
  • Hardware-Accelerated GEMM Operations:
    FP64 FP32 TF32 BF16 FP16 FP8 FP4 INT8 INT4
  • CUDA Compute Capability : n/a

Considerations

  • Lower tensor core count compared to other GPUs
  • Lower memory capacity compared to other GPUs

Specifications for AMD Radeon RX 9060

SpecificationPerformance Ranking
FP32 TFLOPs
33rd @ 21.4 TFLOPs (Entry Tier)(Entry)
FP16 TFLOPs
34th @ 86 TFLOPs (Entry Tier)(Entry)
Tensor Core Count
4th @ 56 Cores
Memory Capacity (GB)
21st @ 8 GB
Memory Bandwidth (GB/s)
20th @ 288 GB/s
Int8 TOPs
29th @ 172 TOPs (Entry Tier)(Entry)
FP8 TFLOPs
9th @ 172 TFLOPs
FP4 TFLOPsData not available

Real-time AMD Radeon RX 9060 GPU Prices

We're tracking 16 of the AMD Radeon RX 9060 GPUs currently available for sale. The lowest average price is $437 (what's this?)
Buy Now

Compare Price/Performance to other GPUs

We track real-time prices of other GPUs too so that you can compare the price/performance of the AMD Radeon RX 9060 GPU to other GPUs.
Compare GPU Price/Performance

Compare AMD Radeon RX 9060 to Another GPU

Compare the AMD Radeon RX 9060 directly to another GPU to see specs, benchmarks, and prices side-by-side.
Compare GPUs Side-by-Side

Price History

AMD Radeon RX 9060 Price History

This chart tracks AMD Radeon RX 9060 prices over the past 6 months based on eBay listings. The yellow line shows the average of the three lowest-priced listings each day—a useful indicator for finding deals.

Trend: Over this period, the lowest average price has been up 20.6%. The current lowest average is $437, compared to a typical $376 over the period. The lowest average price is calculated as the average of the three lowest-priced listings each day.

gpupoet.com

References

Notes

  1. tensorCoreCount tracks the 2nd-generation AI Accelerators as "tensor cores". The RX 9060 has 56 AI Accelerators (2 per CU x 28 CUs).
  2. fp32TFLOPS of 21.4 is sourced directly from the AMD official product page. This reflects RDNA 4 dual-issue FP32 capability; the calculation is 1,792 stream processors x 2,990 MHz x 2 x 2 (dual-issue) = approximately 21.4 TFLOPS.
  3. fp16TFLOPS of 86 represents FP16 Matrix throughput (dense) via the 2nd-gen AI Accelerators (WMMA), as published on the AMD product page (Peak Half Precision (FP16 Matrix) Performance = 86 TFLOPS; with 2:4 structured sparsity = 172 TFLOPS). This is the cross-vendor analog of NVIDIA tensor-core FP16. AMD also publishes FP16 Vector = FP32 Vector = 21.4 TFLOPS (SIMD path); that vector value is NOT used here because it understates AI throughput vs. the matrix path. The existing AMD RDNA 3/4 sibling files in this repo store fp16TFLOPS = 2x FP32 (packed-FP16 architectural capability); those files need migration to the matrix value — see project policy in .claude/agents/gpu-researcher.md.
  4. int8TOPS of 172 represents the non-sparse (dense) INT8 matrix performance per AMD official product page (https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9060.html). RDNA 4 AI accelerators do support 2:4 structured sparsity (the AMD product page also lists 343 TOPS with structured sparsity = 2x dense), but the dense value is used here for consistent cross-vendor comparison per project convention.
  5. fp8TFLOPS of 172 is the peak FP8 Matrix (dense, no structured sparsity) performance per the AMD official product page (https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9060.html), which also lists 343 TFLOPS FP8 Matrix with structured sparsity (2x dense). Dense value used for consistent cross-vendor comparison. This equals both int8TOPS (172) and 2x fp16TFLOPS (86), consistent with AMD's halving-bitwidth-doubles-throughput Matrix Core pattern confirmed across all six RDNA 4 SKUs audited on 2026-09-02 (RX 9070 GRE, AI PRO R9700, RX 9070 XT, RX 9070, RX 9060 XT, RX 9060).
  6. supportedHardwareOperations updated to add FP8 (Phase 5 audit, 2026-09-02), superseding the prior note below that deferred FP8 for consistency with sibling files. AMD's official product page publishes an FP8 Matrix performance row (172 TFLOPS dense) for the RX 9060, confirming 2nd-generation AI Accelerator FP8 support is present on this Navi 44-die SKU. Direct verification this batch confirmed FP8 is published on AMD's official product pages for all six RDNA 4 desktop/workstation SKUs, spanning both the Navi 44 die (this card, plus RX 9060 XT) and the Navi 48 die (RX 9070 GRE/AI PRO R9700/RX 9070/RX 9070 XT), so FP8 WMMA support is architecture-wide (GFX12/RDNA 4), not die-specific. See the canonical RDNA 4 row in .claude/agents/gpu-researcher.md.
  7. fp4TFLOPS is intentionally omitted (not set to null-with-unverifiedSpecs) because no FP4 Matrix row is published on the AMD product page and no FP4 WMMA input format is documented in the RDNA4 Instruction Set Architecture Reference Guide. This is a confirmed hardware negative (RDNA 4 has no FP4 support), not a research gap, so unverifiedSpecs does not apply per project convention.
  8. Memory bandwidth of 288 GB/s calculated as 128-bit interface x 18 Gbps = 288 GB/s, confirmed by AMD official product page and multiple third-party sources.
  9. TDP is 132W Total Board Power per AMD official product page and Guru3D launch coverage.
  10. Process node is TSMC 4nm (N4P) with Navi 44 XL GPU die sized at 199 mm2 and 29.7 billion transistors (same die as RX 9060 XT, with 4 CUs disabled).
  11. Boost clock is 2,990 MHz and game clock is 2,400 MHz per AMD official product page and Wikipedia RX 9000 series specifications table.
  12. PCIe interface is PCIe 5.0 x16, confirmed by Wikipedia Radeon RX 9000 series specifications table and consistent with the RDNA 4 architecture specification.
  13. MSRP is null because the RX 9060 launched on August 5, 2025 as an OEM-only product with no official retail MSRP. AMD confirmed OEM-exclusive availability (source: Wccftech). AMD informally stated a $249-$269 price range if a retail version is ever released, but no official MSRP has been announced. TechSpot review estimates approximately $260 based on system pricing comparisons.
  14. The RX 9060 launched on August 5, 2025 as an OEM-exclusive product (available only through select system integrators in pre-built systems). No retail AIB cards were announced at launch. As of mid-2026, retail AIB partner cards have become available (e.g., ASRock RX 9060 Challenger 8GB OC per Guru3D), so the OEM-only status described at launch no longer reflects the current retail situation. The thirdPartyProducts array should be updated with retail AIB model numbers as they are confirmed.
  15. manufacturerIdentifiers is empty because AMD OPN (Ordering Part Number) codes for consumer GPUs are typically not published in consumer-facing documentation. AMD does not publish OPNs for OEM GPU cards through retail channels.
  16. thirdPartyProducts is empty pending full research of retail AIB partner cards. The RX 9060 launched as OEM-only, but retail cards (e.g., ASRock RX 9060 Challenger 8GB OC) have since become available as of mid-2026. This array should be populated with confirmed retail model numbers and updated accordingly.
  17. FSR 4 is exclusive to RDNA 4 GPUs and leverages the AI accelerators for ML-based upscaling.
This site contains affiliate links. As an eBay Partner and Amazon Associate, gpupoet.com may be compensated if you make a purchase, at no cost to you. Learn more.