Your newly sponsored name will now be SharpAI.
April 1, 2026 at 3:26 PM
Your newly sponsored name will now be SharpAI.
March 21, 2026 at 6:47 PM
MacBook M5 Pro and Qwen3.5 = Local AI Security System
https://www.sharpai.org/benchmark/
https://news.ycombinator.com/item?id=47457107
https://www.sharpai.org/benchmark/
https://news.ycombinator.com/item?id=47457107
HomeSec-Bench — Local AI vs Cloud Benchmark | SharpAI Aegis
Qwen3.5-9B scores 93.8% on 96 real security AI tests — within 4 points of GPT-5.4 — running entirely on Apple Silicon. Full benchmark results and methodology.
www.sharpai.org
March 20, 2026 at 7:30 PM
MacBook M5 Pro and Qwen3.5 = Local AI Security System
https://www.sharpai.org/benchmark/
https://news.ycombinator.com/item?id=47457107
https://www.sharpai.org/benchmark/
https://news.ycombinator.com/item?id=47457107
<a href="https://github.com/SharpAI/SwiftLM" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">github.com/SharpAI/SwiftLM
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-comp...
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-comp...
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app.
github.com
April 3, 2026 at 6:37 AM
<a href="https://github.com/SharpAI/SwiftLM" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">github.com/SharpAI/SwiftLM
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-comp...
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-comp...
📦 SharpAI / DeepCamera
⭐ 2,523 (+68)
🗒 JavaScript
Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your ho...
⭐ 2,523 (+68)
🗒 JavaScript
Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your ho...
GitHub - SharpAI/DeepCamera: Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google, Anthropic or local AI. Runs on Mac Mini & AI PC.
Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, und...
github.com
March 23, 2026 at 4:06 PM
📦 SharpAI / DeepCamera
⭐ 2,523 (+68)
🗒 JavaScript
Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your ho...
⭐ 2,523 (+68)
🗒 JavaScript
Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your ho...
Lets remember ... AUSTRALIA dumped the MF.. and thinks he is a piece of SHIT... human sharpai...
March 31, 2025 at 1:06 PM
Lets remember ... AUSTRALIA dumped the MF.. and thinks he is a piece of SHIT... human sharpai...
MacBook M5 Pro and Qwen3.5 = Local AI Security System | Discussion
HomeSec-Bench — Local AI vs Cloud Benchmark | SharpAI Aegis
Qwen3.5-9B scores 93.8% on 96 real security AI tests — within 4 points of GPT-5.4 — running entirely on Apple Silicon. Full benchmark results and methodology.
www.sharpai.org
March 20, 2026 at 5:20 PM
MacBook M5 Pro and Qwen3.5 = Local AI Security System | Discussion
Swiftコードだけで大規模言語モデルをローカル実行できるライブラリっぽい
Apple製品での推論処理が手軽に実装できそうで気になる
yug1224 starred SharpAI/SwiftLM
https://github.com/SharpAI/SwiftLM
Apple製品での推論処理が手軽に実装できそうで気になる
yug1224 starred SharpAI/SwiftLM
https://github.com/SharpAI/SwiftLM
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app.
github.com
April 2, 2026 at 5:47 PM
Swiftコードだけで大規模言語モデルをローカル実行できるライブラリっぽい
Apple製品での推論処理が手軽に実装できそうで気になる
yug1224 starred SharpAI/SwiftLM
https://github.com/SharpAI/SwiftLM
Apple製品での推論処理が手軽に実装できそうで気になる
yug1224 starred SharpAI/SwiftLM
https://github.com/SharpAI/SwiftLM
HN: TurboQuant brings fast SSD expert streaming and KV compression to M5 Pro & iOS. Promising new tech from SharpAI—check the repo: #HN #AI #OpenSource
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app.
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app. - SharpAI/SwiftLM
github.com
April 1, 2026 at 7:44 PM
HN: TurboQuant brings fast SSD expert streaming and KV compression to M5 Pro & iOS. Promising new tech from SharpAI—check the repo: #HN #AI #OpenSource
⚡ SwiftLMが登場！
Appleシリコン向けに開発された、高速なSwiftによるLLM推論サーバーです。
OpenAI互換APIで動作し、大規模モデルもスムーズに処理可能。
Python不要でメモリ効率も◎。
iOSアプリも搭載で、どこでも使えるのが嬉しいです！
#AI #Swift #AppleSilicon github.com #news
Appleシリコン向けに開発された、高速なSwiftによるLLM推論サーバーです。
OpenAI互換APIで動作し、大規模モデルもスムーズに処理可能。
Python不要でメモリ効率も◎。
iOSアプリも搭載で、どこでも使えるのが嬉しいです！
#AI #Swift #AppleSilicon github.com #news
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app. · GitHub
github.com
April 2, 2026 at 10:02 AM
⚡ SwiftLMが登場！
Appleシリコン向けに開発された、高速なSwiftによるLLM推論サーバーです。
OpenAI互換APIで動作し、大規模モデルもスムーズに処理可能。
Python不要でメモリ効率も◎。
iOSアプリも搭載で、どこでも使えるのが嬉しいです！
#AI #Swift #AppleSilicon github.com #news
Appleシリコン向けに開発された、高速なSwiftによるLLM推論サーバーです。
OpenAI互換APIで動作し、大規模モデルもスムーズに処理可能。
Python不要でメモリ効率も◎。
iOSアプリも搭載で、どこでも使えるのが嬉しいです！
#AI #Swift #AppleSilicon github.com #news
MacBook M5 Pro and Qwen3.5 = Local AI Security System https://www.sharpai.org/benchmark/ (https://news.ycombinator.com/item?id=47457107)
HomeSec-Bench — Local AI vs Cloud Benchmark | SharpAI Aegis
Qwen3.5-9B scores 93.8% on 96 real security AI tests — within 4 points of GPT-5.4 — running entirely on Apple Silicon. Full benchmark results and methodology.
www.sharpai.org
March 20, 2026 at 5:25 PM
MacBook M5 Pro and Qwen3.5 = Local AI Security System https://www.sharpai.org/benchmark/ (https://news.ycombinator.com/item?id=47457107)
July 19, 2026 at 5:34 PM
SharpAI/DeepCamera allows you to run Qwen, DeepSeek, SmolVLM, and LLaVA locally for real-time VLM scene analysis, object detection, and private CCTV surveillance monitoring.
July 19, 2026 at 5:34 PM
SharpAI/DeepCamera allows you to run Qwen, DeepSeek, SmolVLM, and LLaVA locally for real-time VLM scene analysis, object detection, and private CCTV surveillance monitoring.
April 15, 2026 at 12:14 PM
September 25, 2025 at 8:31 PM
Local AI vs Cloud
The Benchmark
Qwen3.5-9B scores 93.8% — within 4 points of GPT-5.4 — running entirely on a MacBook Pro M5 at 25 tok/s, 765ms TTFT, using only 13.8 GB of unified memory. Zero API costs. Full data privacy. All local.
www.sharpai.org/benchmark/
The Benchmark
Qwen3.5-9B scores 93.8% — within 4 points of GPT-5.4 — running entirely on a MacBook Pro M5 at 25 tok/s, 765ms TTFT, using only 13.8 GB of unified memory. Zero API costs. Full data privacy. All local.
www.sharpai.org/benchmark/
HomeSec-Bench — Local AI vs Cloud Benchmark | SharpAI Aegis
Qwen3.5-9B scores 93.8% on 96 real security AI tests — within 4 points of GPT-5.4 — running entirely on Apple Silicon. Full benchmark results and methodology.
www.sharpai.org
March 22, 2026 at 7:29 PM
Local AI vs Cloud
The Benchmark
Qwen3.5-9B scores 93.8% — within 4 points of GPT-5.4 — running entirely on a MacBook Pro M5 at 25 tok/s, 765ms TTFT, using only 13.8 GB of unified memory. Zero API costs. Full data privacy. All local.
www.sharpai.org/benchmark/
The Benchmark
Qwen3.5-9B scores 93.8% — within 4 points of GPT-5.4 — running entirely on a MacBook Pro M5 at 25 tok/s, 765ms TTFT, using only 13.8 GB of unified memory. Zero API costs. Full data privacy. All local.
www.sharpai.org/benchmark/
TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS | Discussion
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app.
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app. - SharpAI/SwiftLM
github.com
April 1, 2026 at 7:00 PM
TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS | Discussion
TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS
Discussion | hackernews | Author: aegis_camera
Discussion | hackernews | Author: aegis_camera
TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS
⚡ Native Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app. - SharpAI/SwiftLM
github.com
April 1, 2026 at 6:38 PM
TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS
Discussion | hackernews | Author: aegis_camera
Discussion | hackernews | Author: aegis_camera
github.com/SharpAI/Swif... Turboquant builds are flying out at high speed...this is exciting but I'm also wondering about some of the edge cases and issues that have been pointed out by critics of the paper. Still, this is exciting as progress in compression and performance is definitely being made!
GitHub - SharpAI/SwiftLM: ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app.
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app. - SharpAI/SwiftLM
github.com
April 1, 2026 at 7:20 PM
github.com/SharpAI/Swif... Turboquant builds are flying out at high speed...this is exciting but I'm also wondering about some of the edge cases and issues that have been pointed out by critics of the paper. Still, this is exciting as progress in compression and performance is definitely being made!