Eliovp reported that Paiton runs FLUX.2 klein 4B at around 1 second per 1024 × 1024 image on a single Radeon AI PRO R9700, four steps, after warmup, achieving around 19% more images per euro than the strongest stock configuration qualified.
Public source
Publisher name
Public post
We’re still building quietly. This time, we’ll let the images do the talking ;-) Paiton runs FLUX.2 klein 4B at around 1 second per 1024 × 1024 image on a single Radeon…
Company
Eliovp
Speeding Up Machines & Accelerating People
- Industry
- IT Services and IT Consulting
- Location
- Sint Gillis Waas, BE
- Company size
- 2–10 employees
About Eliovp
Try to reimagine high performance computing. Now open your eyes. You´re here. If you’re into high-end hardware, this is your happy place. Automated, optimized and fit for the future.
See moreLatest activity
Latest activity from Eliovp
5 signals
Research & Knowledge
Eliovp reported that Paiton runs FLUX.2 klein 4B at around 1 second per 1024 × 1024 image on a single Radeon AI PRO R9700, four steps, after warmup, achieving roughly a third less peak Torch allocation down to 12.9 GiB, with maximum sampled driver VRAM at 14.6 GiB, and the whole model pipeline stays on the GPU with no CPU offload.
Research & Knowledge
Eliovp reported that Paiton runs FLUX.2 klein 4B at around 1 second per 1024 × 1024 image on a single Radeon AI PRO R9700, four steps, after warmup, achieving 16% lower generation latency and 19% more projected images per hour than the strongest stock configuration qualified.
Research & Knowledge
Eliovp announced that Paiton runs FLUX.2 klein 4B at around 1 second per 1024 × 1024 image on a single Radeon AI PRO R9700, four steps, after warmup.
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
Topaz Labs
Topaz Labs received two in-depth GPU performance analyses from Puget Systems for Topaz Video 1.6.1.
Products & Services
EPAM Systems
EPAM Systems introduced a custom model format called Q4_CR GGUF based on INT4 that runs top-tier consumer graphics cards like FLUX.2 Klein 9B and Krea 2 Turbo significantly faster while taking up roughly quarter of the VRAM compared to full precision or half the VRAM compared to the most popular INT8 ConvRot quantization.
Products & Services
Globant
Globant's MiniMax H3 Max optimized by fal can generate around 5 seconds of 768p video in under 3 seconds.
Research & Knowledge
Yantrion Inc
Yantrion Inc measured 975.5 aggregate decode tokens per second across 56 concurrent requests on one 8× AMD Instinct MI350X node using Kimi-K3.
Research & Knowledge
Cloudian Inc