Huawei Ascend 910B
Huawei Ascend 910B specs, benchmarks, and real-world performance. 64GB HBM2e, ~1,200 GB/s bandwidth, ~600 TFLOPS FP16 - the chip that trained DeepSeek.
James Kowalski
AI Benchmarks & Tools Analyst
James is a software engineer turned tech writer who spent six years building backend systems at a fintech startup in Chicago before pivoting to full-time analysis of AI tools and infrastructure. His engineering background means he doesn't just read the spec sheet - he runs the benchmarks, profiles the latency, and checks whether the marketing claims hold up under real workloads.
He studied Computer Science at the University of Illinois at Urbana-Champaign, where he first got hooked on natural language processing during a senior research project on sentiment analysis. He later completed a certificate in data journalism from Northwestern's Medill School.
At Awesome Agents, James owns the leaderboards and tool comparison coverage. He maintains the site's benchmark tracking methodology and is the person who actually runs the numbers before publishing any ranking. He is also an open-source advocate and contributes to several projects in the LLM inference space.
Based in Chicago, IL.
Articles by James Kowalski
Huawei Ascend 910C
Huawei Ascend 910C specs, benchmarks, and performance analysis. 96GB HBM2e, ~1,800 GB/s bandwidth, ~800 TFLOPS FP16 - China's flagship AI chip under US sanctions.
Intel Gaudi 3 - Challenging NVIDIA on Price
Intel Gaudi 3 is a TSMC 5nm AI accelerator with 128GB HBM2e and 1,835 TFLOPS FP8 performance, positioned as a cost-effective alternative to NVIDIA H100 for training and inference workloads.
NVIDIA A100 - The GPU That Built Modern AI
Complete specs, benchmarks, and analysis of the NVIDIA A100 80GB SXM - the Ampere-architecture GPU that remains the most widely deployed AI accelerator in the world.
NVIDIA B200 - Blackwell Flagship GPU
Complete specs, benchmarks, and analysis of the NVIDIA B200 - the Blackwell-architecture flagship GPU with 192GB HBM3e, 8 TB/s bandwidth, and up to 9,000 TFLOPS FP8.
NVIDIA GB200 NVL72 - Rack-Scale Blackwell
Complete specs, benchmarks, and analysis of the NVIDIA GB200 NVL72 - the 72-GPU rack-scale Blackwell system delivering 1,440 PFLOPS FP4 for trillion-parameter AI training and inference.
NVIDIA GB300 NVL72 - Blackwell Ultra Rack
Complete specs, benchmarks, and analysis of the NVIDIA GB300 NVL72 - the Blackwell Ultra rack-scale system with 288GB HBM3e per GPU, 1.5x more FP4 compute, and 2x attention performance over GB200.
NVIDIA H100 SXM - The AI Training Benchmark
Complete specs, benchmarks, and analysis of the NVIDIA H100 SXM - the Hopper-architecture GPU that defined the standard for AI training and inference performance.
NVIDIA H200 - Inference-Optimized Hopper
Complete specs, benchmarks, and analysis of the NVIDIA H200 - the HBM3e-equipped Hopper GPU that delivers 76% more memory and 43% more bandwidth than the H100 for inference workloads.
NVIDIA RTX 3090 - The Budget 24GB Value King
Full specs and benchmarks for the NVIDIA GeForce RTX 3090 - 24GB GDDR6X at 936 GB/s, Ampere architecture, and why used 3090s remain the best value option for local AI inference in 2026.
NVIDIA RTX 4090 - The Home Lab AI Standard
Full specs and benchmarks for the NVIDIA GeForce RTX 4090 - 24GB GDDR6X, 1,008 GB/s bandwidth, Ada Lovelace architecture, and why it remains the default home lab GPU for local AI inference.
NVIDIA RTX 5090 - Blackwell for the Home Lab
Full specs and benchmarks for the NVIDIA GeForce RTX 5090 - 32GB GDDR7, 1,792 GB/s bandwidth, Blackwell architecture, and what it means for local AI inference.
