🏗️ Building on HF

John Locke

johnlockejrr

·

johnlockejrr

AI & ML interests

OCR, HTR, ATR, NLP, AI

Recent Activity

liked a model about 13 hours ago

orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF

reacted to SeaWolf-AI's post with 👀 about 17 hours ago

🖼️ NO GPU, Only CPU : Z-Image model Zero graphics cards. 46 seconds. Photoreal. That laptop you're reading this on. No graphics card, right? It generates images. No CUDA install. No Python environment. No driver changes. One binary, three model files. Done. 📊 Measured — GPU count used: zero 512×512 : 46.4 s Korean prompt : 45.3 s (faster than English) 1024×1024 : 192.7 s Peak RAM : 6.42 GB GPUs used : 0 (Intel Xeon Gold 6526Y ×2, 48 threads, Q4_0, 3 steps) ⚡ From 244 seconds to 46 — 5.3× Run it on defaults and it takes 244 s. Switch to 3 steps and it's 48.6 s. Add VAE tiling and it's 46.4 s. The biggest culprit was the default. Z-Image Turbo is distilled to paint in few strokes, but the tool's default is 20. We were throwing away 5× for no reason. So were we, at first. 3 is the floor. Put 4 and 3 side by side and you cannot tell them apart. At 2 it collapses — water droplets and wood grain vanish, and the surface turns cloth-like. 🔗 Links Model https://huggingface.co/FINAL-Bench/POCKET-Zimage-CPU Live demo Space (runs on CPU) https://huggingface.co/spaces/FINAL-Bench/POCKET-Zimage-CPU POCKET collection https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6

liked a model 2 days ago

orcarouter/OrcaSAQ-2-27B

View all activity

Organizations

johnlockejrr 's models 58

johnlockejrr/RICO-GGUF

27B • Updated 19 days ago • 13

johnlockejrr/regnetx-8gf-polyline-hebrew-samaritan

Object Detection • Updated Aug 22 • 1

johnlockejrr/regnetx-8gf-polyline-baseline-stage0

Object Detection • Updated Aug 22 • 1

johnlockejrr/dfine-det-large-baseline-stage0

Object Detection • Updated Aug 17 • 3

johnlockejrr/convnextv2-polyline-base-hebrew-samaritan

Object Detection • Updated Aug 15 • 1

johnlockejrr/dfine-det-large-baseline-hebrew-samaritan-stage1

Object Detection • Updated Aug 10 • 1

johnlockejrr/ppocrv6-sam-heb

Image-to-Text • Updated Jul 31 • 1

johnlockejrr/LightOnOCR-2-1B-base-nena-ussr

Image-Text-to-Text • 1B • Updated Mar 16 • 6 • 1

johnlockejrr/lagfart_yolo

Updated Feb 25 • 6

johnlockejrr/Qwen2.5-14B-Instruct-mxfp4

Text Generation • 15B • Updated Feb 19 • 33

johnlockejrr/Qwen2.5-7B-Instruct-mxfp4

Text Generation • 8B • Updated Feb 19 • 15

johnlockejrr/Qwen2.5-Coder-14b-mxfp4

Text Generation • 15B • Updated Feb 19 • 77 • 1

johnlockejrr/GLM-OCR-samaritan

Image-to-Text • 1B • Updated Feb 15 • 19 • 1

johnlockejrr/LightOnOCR-2-1B-base-samaritan

Image-Text-to-Text • 1B • Updated Feb 14 • 14

johnlockejrr/LightOnOCR-2-1B-base-samaritan-GGUF

Image-Text-to-Text • 0.6B • Updated Feb 13 • 48

johnlockejrr/Nordic_Multicentury

Object Detection • Updated Jan 4 • 8 • 1

johnlockejrr/marianmt_syr_voc_eastern

Translation • 0.2B • Updated Nov 15, 2025 • 19

johnlockejrr/marianmt_heb_voc

Translation • 61.4M • Updated Nov 10, 2025 • 7

johnlockejrr/marianmt_syr_voc_western

Translation • 0.2B • Updated Nov 10, 2025 • 11

johnlockejrr/marianmt-smp-sam-onnx

Translation • Updated Nov 2, 2025 • 8

johnlockejrr/marianmt-smp-sam

Translation • 61.4M • Updated Nov 2, 2025 • 12

johnlockejrr/aramaic-diacritization-model

61.4M • Updated Jul 30, 2025 • 7

johnlockejrr/opus-arc-targum-vocalization

61.4M • Updated Jul 25, 2025 • 9

johnlockejrr/marianmt-he2arc-targum-voc-shva

Translation • 61.4M • Updated Jul 22, 2025 • 7

johnlockejrr/marianmt-he2arc-targum-voc

Translation • 61.4M • Updated Jul 22, 2025 • 9 • 1

johnlockejrr/marianmt-he2yid-tanakh

Translation • 77.1M • Updated Jul 21, 2025 • 6 • 1

johnlockejrr/marianmt-he2arc-targum

Translation • 61.4M • Updated Jul 15, 2025 • 8 • 1

johnlockejrr/marianmt-he2arc-sam

Translation • 61.4M • Updated Jul 15, 2025 • 6 • 1

johnlockejrr/marianmt-en2he-nwt

77.9M • Updated Jul 14, 2025 • 5 • 1

johnlockejrr/marianmt-he2en-nwt

77.1M • Updated Jul 13, 2025 • 4 • 1