AMD Ryzen AI 5 340 vs NVIDIA RTX Spark (MediaTek AHJ11488B) Comparison

AMD
AMD

AMD Ryzen AI 5 340

CORE STATE Krackan Point
CORE SPECS 6 Cores / 12 Threads
CLOCK SPEED 2 Base / 4.8 GHz Turbo
CACHE 8 MB
MAX TDP 28W
ARCHITECTURE Zen 5
nm
PROCESS 4 nm
LAUNCH DATE 2025
VS
Unknown
CPU

RTX Spark (MediaTek AHJ11488B)

CORE STATE N1X
CORE SPECS 20 Cores / 20 Threads
CLOCK SPEED 1.7 Base / 4 GHz Turbo
CACHE 8 MB (shared)
MAX TDP 38W
ARCHITECTURE N1X
nm
PROCESS 3 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

cinebench_cinebench_r15_multicore
1,915
N/A
cinebench_cinebench_r15_singlecore
242.6
N/A
cinebench_cinebench_r23_multicore
12,532
N/A
cinebench_cinebench_r23_singlecore
1,915.5
N/A
geekbench_multicore
9,165
N/A
geekbench_singlecore
2,140
N/A
passmark_data_compression
229,796
N/A
passmark_data_encryption
11,470
N/A
passmark_extended_instructions
16,440
N/A
passmark_find_prime_numbers
72
N/A
passmark_floating_point_math
39,967
N/A
passmark_integer_math
63,078
N/A
passmark_multithread
19,506
N/A
passmark_physics
1,095
N/A
passmark_random_string_sorting
24,970
N/A
passmark_single_thread
3,683
N/A
passmark_singlethread
3,683
N/A

Analysis: AMD Ryzen AI 5 340 vs NVIDIA RTX Spark (MediaTek AHJ11488B)

AMD Ryzen AI 5 340 vs NVIDIA RTX Spark (MediaTek AHJ11488B)

Head-to-Head Benchmarks

The benchmark data for this comparison is one-sided. The AMD Ryzen AI 5 340 has a complete set of recorded measurements across Cinebench, Geekbench, and Passmark tests. The NVIDIA RTX Spark (MediaTek AHJ11488B) currently has no recorded benchmark scores in the database, which means a direct head-to-head comparison of measured performance cannot be constructed from the available data. All wins in this section belong to the Ryzen AI 5 340 by default, but only because the RTX Spark has not been measured.

The Ryzen AI 5 340 posts a Cinebench R23 multi-core score of 12532 and a single-core score of 1915.5. In the older Cinebench R15 test, it records 1915 multi-core and 242.6 single-core. Geekbench results show 9165 multi-core and 2140 single-core. The Passmark suite shows a multithread score of 19506, a single-thread score of 3683, integer math at 63078, floating point math at 39967, and extended instructions at 16440. Data compression reaches 229796, encryption reaches 11470, prime number finding reaches 72, random string sorting reaches 24970, and physics reaches 1095.

These numbers indicate a processor that performs strongly across both integer and floating point workloads. The single-thread Passmark score of 3683 is particularly notable, as it appears twice in the database under slightly different test names (passmark_single_thread and passmark_singlethread), confirming consistency in the measurement. The multi-core Cinebench R23 score of 12532 places the chip well above typical mobile processors, and the Geekbench multi-core score of 9165 reinforces that position.

The RTX Spark has no scores to compare against. Its average benchmark score is listed as 0, and its percentile versus all CPUs is 50, which appears to be a placeholder rather than a measured result. The database shows zero wins for each processor in the head-to-head section, further confirming that no direct comparison data exists.

Because the RTX Spark is marked as unreleased with a production status of unreleased, the absence of benchmarks is expected. The Ryzen AI 5 340 is marked as active and has been measured extensively. The data shows that any performance comparison between these two processors must rely on the Ryzen AI 5 340's recorded results alone until the RTX Spark is benchmarked.

FAQ

Q: Which processor has higher measured multi-core performance?

A: Only the AMD Ryzen AI 5 340 has recorded multi-core scores. It reaches 12532 in Cinebench R23 multi-core, 9165 in Geekbench multi-core, and 19506 in Passmark multithread. The NVIDIA RTX Spark has no recorded benchmarks in the database, so no comparison is possible.

Q: What is the Ryzen AI 5 340's standing relative to other CPUs?

A: The Ryzen AI 5 340 sits at the 78th percentile versus all CPUs in the database. Its average benchmark score is 25981. Its nearest rival, the Intel Core i7-14701TE, has an average score of 26013, which is 0.1 percent higher. The AMD Ryzen 5 PRO 5655GE scores 25880, which is 0.4 percent lower, and the AMD Ryzen 5 8640HS scores 26106, which is 0.5 percent higher.

Q: Does the RTX Spark have any benchmark wins?

A: No. The RTX Spark has an empty benchmark array, an average benchmark score of 0, and no nearest rivals listed. The head-to-head section shows zero wins for both processors.

Q: Which processor has a higher clock speed?

A: The Ryzen AI 5 340 has a base clock of 2.00 GHz and a boost clock of 4.80 GHz. The RTX Spark has a base clock of 1.70 GHz and a boost clock of 4.00 GHz. Both figures are higher on the Ryzen AI 5 340.

Q: How do the core counts compare?

A: The RTX Spark has 20 cores and 20 threads, while the Ryzen AI 5 340 has 6 cores and 12 threads. The RTX Spark has more cores, but the Ryzen AI 5 340 has simultaneous multithreading, which the RTX Spark lacks.

Q: Which processor has a higher memory bandwidth?

A: The RTX Spark has a quad-channel memory bus with 273.1 GB/s bandwidth. The Ryzen AI 5 340 has a dual-channel memory bus with 89.6 GB/s bandwidth. The RTX Spark's bandwidth is substantially higher in the recorded specifications.

Architecture Differences

The two processors come from different design philosophies. The AMD Ryzen AI 5 340 uses the Zen 5 architecture under the Krackan Point codename, part of the Ryzen AI 300 generation that combines Zen 5 and Zen 5c cores. It is built on a 4 nm process at TSMC with a die size of 195 mm². The RTX Spark uses the N1X codename under the Spark (GB10) generation, built on a 3 nm process at TSMC with a die size of 208 mm². The foundry is the same for both, but the process node is smaller on the RTX Spark.

Cache hierarchies differ significantly. The Ryzen AI 5 340 has 80 KB of L1 cache per core, 1 MB of L2 per core, and 8 MB of L3. The RTX Spark has 128 KB of L1 per core, 2 MB of L2 per core, and 8 MB of shared L3. The RTX Spark's per-core L1 and L2 caches are larger, while the total L3 is identical at 8 MB.

The Ryzen AI 5 340 supports DDR5 and LPDDR5X memory over a dual-channel bus. The RTX Spark supports only LPDDR5X over a quad-channel bus. Neither processor supports ECC memory. The Ryzen AI 5 340 uses PCIe Gen 4 with 16 lanes (CPU only), while the RTX Spark has no PCIe support listed in the database.

Integrated graphics also differ. The Ryzen AI 5 340 includes Radeon 840M graphics. The RTX Spark includes a GB20B "Blackwell" integrated GPU. Both are mobile processors, but the Ryzen AI 5 340 is active while the RTX Spark is unreleased.

The Verdict

The data supports a straightforward conclusion: the AMD Ryzen AI 5 340 is the only processor in this comparison with measured performance. Its benchmark scores across Cinebench, Geekbench, and Passmark are complete and internally consistent. The RTX Spark has no recorded benchmarks, no nearest rivals, and an average score of zero. It is also marked as unreleased, which explains the missing data.

For any workload that requires measured performance, the Ryzen AI 5 340 is the only option with evidence. It delivers strong multi-core results (12532 in Cinebench R23, 9165 in Geekbench) and solid single-core results (1915.5 in Cinebench R23, 3683 in Passmark). Its 78th percentile ranking versus all CPUs indicates it sits above the majority of processors in the database.

The RTX Spark cannot be evaluated for performance from the available data. Its specifications show higher core count (20 versus 6), higher memory bandwidth (273.1 GB/s versus 89.6 GB/s), and a smaller process node (3 nm versus 4 nm), but these are architectural facts, not measured outcomes. The database records no evidence of how these specifications translate into real-world performance.

The verdict is clear: pick the Ryzen AI 5 340 if you need a processor with verified benchmark results. The RTX Spark remains an unknown quantity until its measurements are recorded.

Specification Differences

The two processors differ across several specification fields. The Ryzen AI 5 340 has 6 cores and 12 threads, while the RTX Spark has 20 cores and 20 threads. Base clock speeds are 2.00 GHz for the Ryzen AI 5 340 and 1.70 GHz for the RTX Spark. Boost clocks are 4.80 GHz and 4.00 GHz respectively. The Ryzen AI 5 340 has a TDP of 28, while the RTX Spark has a TDP of 38.

The Ryzen AI 5 340 uses AMD Socket FP8, while the RTX Spark has no socket listed. The Ryzen AI 5 340 uses the Zen 5 architecture with the Krackan Point codename. The RTX Spark lists no architecture and uses the N1X codename. The Ryzen AI 5 340 belongs to the Ryzen AI 300 generation (Zen 5 / Zen 5c), while the RTX Spark belongs to the Spark (GB10) generation.

Process nodes are 4 nm for the Ryzen AI 5 340 and 3 nm for the RTX Spark, both at TSMC. Die sizes are 195 mm² and 208 mm². Cache configurations are 80 KB L1 per core and 1 MB L2 per core for the Ryzen AI 5 340, versus 128 KB L1 per core and 2 MB L2 per core for the RTX Spark. Both have 8 MB of L3 cache.

Memory support differs: the Ryzen AI 5 340 supports DDR5 and LPDDR5X over a dual-channel bus with 89.6 GB/s bandwidth, while the RTX Spark supports only LPDDR5X over a quad-channel bus with 273.1 GB/s bandwidth. The Ryzen AI 5 340 has PCIe Gen 4 with 16 lanes (CPU only), while the RTX Spark has no PCIe support. Integrated graphics are Radeon 840M for the Ryzen AI 5 340 and GB20B "Blackwell" for the RTX Spark. The Ryzen AI 5 340 is active and released on 2025-01-05, while the RTX Spark is unreleased with a release date of 2025-12-31.

Where Each One Wins

The Ryzen AI 5 340 wins in every measured category because it is the only processor with benchmark data. It shows strength in multi-threaded workloads (Cinebench R23 multi-core at 12532, Passmark multithread at 19506), single-threaded workloads (Cinebench R23 single-core at 1915.5, Passmark single-thread at 3683), and specialized tasks including data compression (229796), encryption (11470), extended instructions (16440), integer math (63078), floating point math (39967), prime number finding (72), random string sorting (24970), and physics (1095).

The RTX Spark wins in specification-based comparisons only. It has more cores (20 versus 6), which could benefit highly parallel workloads if the architecture scales accordingly. It has a quad-channel memory bus with 273.1 GB/s bandwidth, which is over three times the Ryzen AI 5 340's 89.6 GB/s. It has a smaller process node (3 nm versus 4 nm), which typically indicates improved power efficiency potential. It also has larger per-core L1 and L2 caches (128 KB and 2 MB versus 80 KB and 1 MB).

However, these specification advantages have no measured confirmation. The database shows no benchmarks for the RTX Spark, so any claim about its real-world performance would be unsupported. The Ryzen AI 5 340's wins are empirical. The RTX Spark's advantages are theoretical, based solely on its listed specifications. Until the RTX Spark is released and benchmarked, the Ryzen AI 5 340 remains the only processor with demonstrated performance in the database.

DETAILED SPECIFICATIONS

SPECIFICATION
AI 5 340
RTX Spark (MediaTek AHJ11488B)
Core Specs
Cores
6
20 +233.3%
Threads
12
20 +66.7%
Base Clock (GHz)
2
1.7 -15.0%
Boost Clock (GHz)
4.8
4 -16.7%
Frequency (GHz)
2
1.7 -15.0%
Turbo Clock (GHz)
4.8
4 -16.7%
Multiplier
20
17 -15.0%
SMP CPUs
1
1 0.0%
Cache
L1 Cache
80 KB (per core)
128 KB (per core)
L2 Cache
1 MB (per core)
2 MB (per core)
L3 Cache
8 MB
8 MB (shared)
L4 Cache
—
16 MB (shared)
Power
TDP (W)
28
38 +35.7%
PL1
—
37.5 W
PL2
—
64 W
Configurable TDP
15-54 W
—
Architecture
Architecture
Zen 5
—
Codename
Krackan Point
N1X
Generation
Ryzen AI 300 (Zen 5 / Zen 5c)
Spark (GB10)
Process Size
4 nm
3 nm
Die Size
195 mm²
208 mm²
Foundry
TSMC
TSMC
Memory
Memory Support
DDR5, LPDDR5X
LPDDR5X
Memory Bus
Dual-channel
Quad-channel
Memory Bandwidth
89.6 GB/s
273.1 GB/s
ECC Memory
No
No
Platform
Socket
AMD Socket FP8
—
PCIe
Gen 4, 16 Lanes(CPU only)
—
Intel Hybrid
Hybrid Cores
3 + 3
10 + 10
E-Core Frequency
2000 MHz up to 3.4 GHz
1500 MHz up to 2.8 GHz
AI/NPU
NPU
Yes / 50 TOPS
—
Graphics
Integrated Graphics
Radeon 840M
GB20B "Blackwell"
Other
Market
Mobile
Mobile
Production Status
Active
unreleased
Part Number
100-000001602
GSE1-675-A1
Package
FP8
FC-BGA
Tj Max
100°C
—
Bundled Cooler
—
Yes
View Ryzen AI 5 340 Details View RTX Spark (MediaTek AHJ11488B) Details