--- title: "GPU Library | Aguasto" description: "A curated manufacturer specification library for AI accelerators and rack systems. Compare like categories with source, unit and configuration boundaries." canonical: "https://www.aguasto.com/gpus" last-updated: "2026-10-12" --- # GPU Library | Aguasto Canonical HTML: [GPU Library](https://www.aguasto.com/gpus) > A curated manufacturer specification library for AI accelerators and rack systems. Compare like categories with source, unit and configuration boundaries. [Resources](https://www.aguasto.com/resources) [GPU Library](https://www.aguasto.com/gpus) [Model Index](https://www.aguasto.com/models) [Inference Stack](https://www.aguasto.com/inference-stack) [Learn](https://www.aguasto.com/learn) [Insights](https://www.aguasto.com/insights) [Research](https://www.aguasto.com/research) [Engineering tools](https://www.aguasto.com/tools) Aguasto / gpus ## The GPU Library. Accelerators and rack systems, with the boundaries that make comparisons useful. Manufacturer specifications, configuration differences and deployment considerations—not a list of available Aguasto inventory. Original Aguasto conceptual illustration. Not manufacturer geometry, an operating Aguasto asset, or a measured benchmark. Aguasto Research documents third-party hardware, models and software. References do not represent Aguasto inventory, evaluated deployments or available inference services. [Compare compatible hardware →](https://www.aguasto.com/gpus/compare) Search hardwareCategoryAllIndividual acceleratorRack systemCharacteristicAllAMDBlackwellBlackwell UltraCDNA 3CDNA 4CDNA 5Grace BlackwellGrace Blackwell UltraHopperMI455X / EPYC Venice / PensandoNVIDIAVera CPU / Rubin GPUClear filters 12 of 12 references Individual accelerator ### NVIDIA H100 SXM Hopper. 80 GB published memory. A documented commercial SXM accelerator; this record does not establish supplier stock or an Aguasto allocation. Manufacturer reference · reviewed Oct 12, 2026 [NVIDIA H100 SXM](https://www.aguasto.com/gpus/h100) Individual accelerator ### NVIDIA H200 SXM Hopper. 141 GB published memory. The manufacturer product page explicitly says available. No supplier stock or Aguasto deployment is verified. Manufacturer reference · reviewed Oct 12, 2026 [NVIDIA H200 SXM](https://www.aguasto.com/gpus/h200) Individual accelerator ### NVIDIA B200 SXM Blackwell. 180 GB published memory. NVIDIA's HGX page states HGX B200 is shipping. This record describes one SXM GPU, not the baseboard. Manufacturer reference · reviewed Oct 12, 2026 [NVIDIA B200 SXM](https://www.aguasto.com/gpus/b200) Individual accelerator ### NVIDIA B300 Blackwell Ultra. Configuration-dependent memory. NVIDIA states HGX B300 is shipping. A single generic capacity is withheld because current manufacturer documents describe different configurations. Manufacturer reference · reviewed Oct 12, 2026 [NVIDIA B300](https://www.aguasto.com/gpus/b300) Rack system ### NVIDIA GB200 NVL72 Grace Blackwell. 13,400 GB published memory. NVIDIA reports GB200 NVL72 shipments began in 2024. Availability of a specific OEM build remains supplier-specific. Manufacturer reference · reviewed Oct 12, 2026 [NVIDIA GB200 NVL72](https://www.aguasto.com/gpus/gb200-nvl72) Rack system ### NVIDIA GB300 NVL72 Grace Blackwell Ultra. 20,000 GB published memory. NVIDIA reports GB300 NVL72 shipped in 2025; a specific OEM configuration and delivery date still require confirmation. Manufacturer reference · reviewed Oct 12, 2026 [NVIDIA GB300 NVL72](https://www.aguasto.com/gpus/gb300-nvl72) Rack system ### NVIDIA Vera Rubin NVL72 Vera CPU / Rubin GPU. 20,700 GB published memory. Manufacturer disclosures describe systems shipping and production racks delivered by September 2026. This establishes a shipping ramp, not universal availability or an Aguasto allocation. Manufacturer reference · reviewed Oct 12, 2026 [NVIDIA Vera Rubin NVL72](https://www.aguasto.com/gpus/vera-rubin-nvl72) Individual accelerator ### AMD Instinct MI300X CDNA 3. 192 GB published memory. Launched accelerator with manufacturer-reported deployment/benchmark evidence; supplier stock and Aguasto availability are not verified. Manufacturer reference · reviewed Oct 12, 2026 [AMD Instinct MI300X](https://www.aguasto.com/gpus/mi300x) Individual accelerator ### AMD Instinct MI325X CDNA 3. 256 GB published memory. Launched accelerator with manufacturer-reported deployment/benchmark evidence; supplier stock and Aguasto availability are not verified. Manufacturer reference · reviewed Oct 12, 2026 [AMD Instinct MI325X](https://www.aguasto.com/gpus/mi325x) Individual accelerator ### AMD Instinct MI355X CDNA 4. 288 GB published memory. Launched accelerator with manufacturer-reported deployment/benchmark evidence; supplier stock and Aguasto availability are not verified. Manufacturer reference · reviewed Oct 12, 2026 [AMD Instinct MI355X](https://www.aguasto.com/gpus/mi355x) Individual accelerator ### AMD Instinct MI455X CDNA 5. 432 GB published memory. AMD lists a July 2026 launch and published specifications. Reviewed Helios sources still describe partner volume deployments as expected in the second half of 2026; broad shipment availability is not independently established here. Manufacturer reference · reviewed Oct 12, 2026 [AMD Instinct MI455X](https://www.aguasto.com/gpus/mi455x) Rack system ### AMD Helios MI455X / EPYC Venice / Pensando. 31,000 GB published memory. AMD explicitly identifies Helios as a reference design rather than an AMD product for sale. The reviewed page expects OEM/ODM volume deployments in the second half of 2026. Manufacturer reference · reviewed Oct 12, 2026 [AMD Helios](https://www.aguasto.com/gpus/helios) ## Company navigation - [Home](https://www.aguasto.com/) - [Infrastructure](https://www.aguasto.com/infrastructure) - [GPU Cloud](https://www.aguasto.com/gpu-cloud) - [AI Inference](https://www.aguasto.com/ai-inference) - [Development & Investment](https://www.aguasto.com/development) - [Company](https://www.aguasto.com/company) - [Contact](https://www.aguasto.com/contact) - [Privacy](https://www.aguasto.com/privacy) - [Resources](https://www.aguasto.com/resources) - [GPU Library](https://www.aguasto.com/gpus) - [Model Index](https://www.aguasto.com/models) - [Inference Stack](https://www.aguasto.com/inference-stack) - [Learn](https://www.aguasto.com/learn) - [Insights](https://www.aguasto.com/insights) - [Research](https://www.aguasto.com/research) - [Industry cases](https://www.aguasto.com/research/cases) - [Why Modular](https://www.aguasto.com/why-modular) - [Partners](https://www.aguasto.com/partners) - [GPU comparison](https://www.aguasto.com/gpus/compare) - [Model comparison](https://www.aguasto.com/models/compare) - [Engineering tools](https://www.aguasto.com/tools) - [Development friction](https://www.aguasto.com/research/hyperscale-development-friction) - [NVIDIA H100 SXM](https://www.aguasto.com/gpus/h100) - [NVIDIA H200 SXM](https://www.aguasto.com/gpus/h200) - [NVIDIA B200 SXM](https://www.aguasto.com/gpus/b200) - [NVIDIA B300](https://www.aguasto.com/gpus/b300) - [NVIDIA GB200 NVL72](https://www.aguasto.com/gpus/gb200-nvl72) - [NVIDIA GB300 NVL72](https://www.aguasto.com/gpus/gb300-nvl72) - [NVIDIA Vera Rubin NVL72](https://www.aguasto.com/gpus/vera-rubin-nvl72) - [AMD Instinct MI300X](https://www.aguasto.com/gpus/mi300x) - [AMD Instinct MI325X](https://www.aguasto.com/gpus/mi325x) - [AMD Instinct MI355X](https://www.aguasto.com/gpus/mi355x) - [AMD Instinct MI455X](https://www.aguasto.com/gpus/mi455x) - [AMD Helios](https://www.aguasto.com/gpus/helios) - [GLM-4.5](https://www.aguasto.com/models/glm-4-5) - [Qwen3-235B-A22B](https://www.aguasto.com/models/qwen3-235b-a22b) - [DeepSeek-R1](https://www.aguasto.com/models/deepseek-r1) - [Llama 3.3 70B Instruct](https://www.aguasto.com/models/llama-3-3-70b-instruct) - [Gemma 3 27B IT](https://www.aguasto.com/models/gemma-3-27b-it) - [gpt-oss-120b](https://www.aguasto.com/models/gpt-oss-120b) - [Kimi-K2-Instruct](https://www.aguasto.com/models/kimi-k2-instruct) - [vLLM](https://www.aguasto.com/inference-stack/vllm) - [SGLang](https://www.aguasto.com/inference-stack/sglang) - [TensorRT-LLM](https://www.aguasto.com/inference-stack/tensorrt-llm) - [NVIDIA Dynamo](https://www.aguasto.com/inference-stack/dynamo) - [NVIDIA Triton Inference Server](https://www.aguasto.com/inference-stack/triton) - [AMD ROCm](https://www.aguasto.com/inference-stack/rocm) - [Ray Serve](https://www.aguasto.com/inference-stack/ray-serve) - [Kubernetes GPU orchestration — NVIDIA device plugin](https://www.aguasto.com/inference-stack/kubernetes) - [Model weights are only the beginning of the memory budget](https://www.aguasto.com/learn/model-weights-and-runtime-memory) - [Why tokens per second is not enough to benchmark inference](https://www.aguasto.com/research/inference-benchmark-methodology) - [Prefill, decode and the cost of separating them](https://www.aguasto.com/learn/prefill-decode-and-disaggregated-serving) - [Choosing between vLLM, SGLang and TensorRT-LLM](https://www.aguasto.com/learn/choosing-an-inference-serving-framework) - [From Power to Inference—Building a Distributed AI Compute Network](https://www.aguasto.com/learn/from-power-to-inference) - [Dedicated compute and shared inference: compare the whole workload](https://www.aguasto.com/insights/dedicated-and-shared-inference-economics) - [Distributed inference reliability begins with the failure boundary](https://www.aguasto.com/learn/distributed-inference-reliability) - [Core Scientific: reading contracted, energized and billed capacity](https://www.aguasto.com/research/cases/core-scientific-capacity-disclosures) - [Why Modular AI Infrastructure Matters Now](https://www.aguasto.com/research/why-modular-ai-infrastructure-matters-now) - [Official LinkedIn](https://www.linkedin.com/company/aguasto) This is a generated representation of the public HTML page. Diagrams are conceptual. GPU and inference services are planned and are not currently available to book or call. The contact page describes the available inquiry flow.