CPU Comparison
Intel Xeon 6736P vs Intel Xeon 6745P
A side-by-side comparison of specs, performance and value. The Intel Xeon 6736P is a 36-core, 72-thread server processor based on the Granite Rapids-SP architecture, built on Intel’s 3 process and targeted at dual-socket enterprise, cloud, and AI-adjacent workloads requiring high memory bandwidth and strong per-core performance.
The Bottom Line
Overview & Launch
Specifications Compared
Performance Compared
Productivity
Gaming
Virtualization
Efficiency
Specialized Performance
AI / ML
- AMX and DL Boost accelerate matrix operations for inference.
- Best suited for CPU-hosted inference models or pre-/post-processing alongside discrete accelerators.
- Not a replacement for high-end GPUs or specialized AI accelerators for training.
- AMX and AVX-512 provide strong CPU-based AI inference
- Best suited for inference and mid-size models when GPUs are not used
- Large memory capacity benefits model serving and data preprocessing
Content Creation
Gaming
- No integrated graphics; requires discrete GPU.
- Platform optimized for server workloads, not client gaming.
- Latency and driver stack not tuned for gaming.
- Single-thread performance is good, but not competitive with best gaming CPUs.
- Server-focused CPU without integrated graphics
- Gaming performance is not a design priority
- Frame rates will be sufficient but not class-leading compared to desktop CPUs
Industry Impact
Best CPU by Use Case
Target Audience
Strengths & Weaknesses
Pros
- 36 high-efficiency P-cores with 72 threads for dense server workloads.
- 8-channel DDR5-6400 with up to 4 TB per socket and high bandwidth.
- 88 PCIe 5.0 lanes for GPUs, NVMe, and SmartNICs.
- Integrated accelerators (AMX, QAT, DLB, DSA, IAA) for AI, crypto, and data processing.
- Granular SST-PP and SST-BF tuning for per-core clock and TDP optimization.
- Strong security feature set including TDX, SGX, and MK-TME for confidential computing.
Cons
- No integrated graphics; requires discrete GPU for any display output.
- Not optimized for gaming or client workloads.
- Platform is server-only; LGA4710 motherboards are not desktop boards.
- Higher platform cost compared to older Sapphire Rapids systems.
- Core count is modest versus top Granite Rapids-SP SKUs that reach 86+ cores.
Pros
- 32 cores and 64 threads for high multi-threaded throughput
- 336 MB L3 cache reduces memory latency for large working sets
- Eight-channel DDR5-6400 with up to 4 TB capacity
- 88 PCIe 5.0 lanes for substantial I/O expansion
- AMX and AVX-512 improve AI and HPC performance
- Mature server ecosystem with RAS features (SGX, TDX, QAT, etc.)
Cons
- 300 W TDP requires robust cooling and power delivery
- New LGA4710 platform forces a full server/platform refresh
- High platform cost relative to older Xeon generations
- Locked multiplier limits tuning flexibility
- Efficiency at light loads is not a strength
Competitors & Alternatives
Intel Xeon 6736P
- AMD EPYC 9334Rival
Server
- AMD EPYC 8324PRival
Server
- Compare head-to-headIntel Xeon 6706P-BRival
Server
- Compare head-to-headIntel Xeon 6726P-BRival
Server
- Intel Xeon Gold 6530Rival
Server
Lower core count (16) but higher base and turbo clocks for workloads that benefit more from per-core performance than raw core count.
Compare head-to-head
Intel Xeon 6745P
- Intel Xeon 6730PRival
Server / 32-core Granite Rapids-SP, 250 W TDP
- Compare head-to-headIntel Xeon 6731PRival
Server / 32-core Granite Rapids-SP, 245 W TDP
- AMD EPYC 9354Rival
Server / 32-core Genoa, DDR5-4800, 280 W TDP
- AMD EPYC 9374FRival
Server / 32-core Genoa, higher clocks, 320 W TDP
- AMD EPYC 9354PRival
Server / 32-core Genoa, single-socket optimized variant
Higher core-count (64-core) Granite Rapids-SP SKU when more threads are needed and TDP budget allows.
Compare head-to-head
Our Verdict on Each
A balanced Granite Rapids-SP SKU that pairs 36 P-cores with strong I/O and accelerators, ideal for consolidating older 2S clusters or building new general-purpose + AI inference nodes.
Best for: New or refreshed dual-socket servers for virtualization, databases, and mixed enterprise + AI inference workloads where you want strong per-core performance, high memory bandwidth, and integrated accelerators without moving to the highest core-count SKUs.
Read the full reviewA powerful 32-core Granite Rapids-SP CPU that excels in memory-bandwidth-sensitive and I/O-heavy server workloads, but its 300 W TDP and platform cost limit it to professional deployments where those features justify the investment.
Best for: Dual-socket servers or workstations running memory-intensive, I/O-heavy workloads such as large databases, virtualization, or AI inference where the 6745P’s cache and memory bandwidth justify the platform cost.
Read the full reviewFrequently Asked Questions
Which is better, Intel Xeon 6736P or Intel Xeon 6745P?
Based on our editorial ratings, the Intel Xeon 6736P comes out ahead with a score of 8.8/10. That said, the best choice depends on your workload — check the spec and performance breakdown above for gaming, productivity and efficiency differences.
Which is faster for gaming, Intel Xeon 6736P or Intel Xeon 6745P?
For gaming, the Intel Xeon 6736P leads with a gaming performance score of 30/100 among Intel Xeon 6736P and Intel Xeon 6745P.
Which uses less power?
The Intel Xeon 6736P has the lowest rated TDP. Power draw across these chips: Intel Xeon 6736P (205 W), Intel Xeon 6745P (300 W).
Do Intel Xeon 6736P and Intel Xeon 6745P use the same socket?
No. They use different sockets (Intel Xeon 6736P: FCLGA4710, Intel Xeon 6745P: FCLGA4710 (LGA4710)), so each needs a compatible motherboard.
Which has more cores?
The Intel Xeon 6736P has the most cores. Core counts: Intel Xeon 6736P (36 cores), Intel Xeon 6745P (32 cores).
Which is faster in multi-core benchmarks?
The Intel Xeon 6736P posts the highest multi-core benchmark score. Multi-core results: Intel Xeon 6736P (44,000), Intel Xeon 6745P (0). Benchmark figures are approximate and workload-dependent.