地端 AI 實驗室

Podcast

地端 AI 實驗室

每天精選 1~3 個可以下載到自己機器上跑的開源模型與 LoRA,用輕鬆對話帶你掌握它能用在哪些場景、你的顯卡跑不跑得動、跟同類差在哪。本節目為情報策展,功能與硬體規格一律引述官方 model card,未經我方實測,更多內容請見 (https://blog.markkulab.net)

35 episodes

Haru-4B 4B-parameter direct speech-to-speech runs offline translation on 16GB VRAM, Edge AI Lab

Haru-4B 4B-parameter direct speech-to-speech runs offline translation on 16GB VRAM, Edge AI Lab

Mark Ku·

18MB, 70x Real-Time: The TTS Model tiny-voca Runs Without a GPU|Local AI Lab

18MB, 70x Real-Time: The TTS Model tiny-voca Runs Without a GPU|Local AI Lab

Mark Ku·

🧪 0.8B Beats 9B: Why dale-0.8b's Offline Command-Guessing Is So Impressive | Local AI Lab

🧪 0.8B Beats 9B: Why dale-0.8b's Offline Command-Guessing Is So Impressive | Local AI Lab

Mark Ku·

🧪 Not training, just tweaking nine weight matrices: qwen-concept-27b sparks heated debate on HN, Local AI Lab

🧪 Not training, just tweaking nine weight matrices: qwen-concept-27b sparks heated debate on HN, Local AI Lab

Mark Ku·

🧪 AutoTrust-Decider-Pro-Vision-27B downloaded 158K times: deciding who AI Agents should trust | Local AI Lab

🧪 AutoTrust-Decider-Pro-Vision-27B downloaded 158K times: deciding who AI Agents should trust | Local AI Lab

Mark Ku·

🧪 6.1 M‑download 27B model: Unsloth‑edition Qwen 3.8 lets you run multimodal fine‑tuning on a 24 GB GPU | Local AI Lab

🧪 6.1 M‑download 27B model: Unsloth‑edition Qwen 3.8 lets you run multimodal fine‑tuning on a 24 GB GPU | Local AI Lab

Mark Ku·

🧪 Arete-27B 24GB 跑、0.5B TTS 4GB 跑:本週精選|地端 AI 實驗室

🧪 Arete-27B 24GB 跑、0.5B TTS 4GB 跑:本週精選|地端 AI 實驗室

Mark Ku·

Qwen3 GGUF surpasses 6 million downloads, Arete‑27B uncensored, ZONOS3‑Mini lightweight voice: Local AI Lab

Qwen3 GGUF surpasses 6 million downloads, Arete‑27B uncensored, ZONOS3‑Mini lightweight voice: Local AI Lab

Mark Ku·

🧪 Official multimodal 290k downloads, 9B uncensored, zero GPU voice: three offline tools this episode | Local AI Lab

🧪 Official multimodal 290k downloads, 9B uncensored, zero GPU voice: three offline tools this episode | Local AI Lab

Mark Ku·

🧪 0.3B Can Run LLM Too? This int4 Model Lets Pi Zero Run Command Classification Offline | Edge AI Lab

🧪 0.3B Can Run LLM Too? This int4 Model Lets Pi Zero Run Command Classification Offline | Edge AI Lab

Mark Ku·

🧪 Thinking tokens slashed to 1/10: Qwen3.8-27B-TURBO-Fable-Cold-Fusion hits 1.5M cumulative downloads|Local AI Lab

🧪 Thinking tokens slashed to 1/10: Qwen3.8-27B-TURBO-Fable-Cold-Fusion hits 1.5M cumulative downloads|Local AI Lab

Mark Ku·

🧪 The 321B GLM-5.3-Flash won't fit on a single GPU, but this 9B model's popularity shot up to 113 | On-Premise AI Lab

🧪 The 321B GLM-5.3-Flash won't fit on a single GPU, but this 9B model's popularity shot up to 113 | On-Premise AI Lab

Mark Ku·

探索十大熱門分類

#1
AI

AI

39 articles
#2
DevOps

DevOps

32 articles
#3
Frontend

Frontend

39 articles
Management

Management

25 articles
Infra

Infra

22 articles
PowerShell

PowerShell

15 articles
Travel

Travel

12 articles
E-Commerce

E-Commerce

11 articles
.NET Core

.NET Core

11 articles
Cloud

Cloud

10 articles

Subscribe to Newsletter

Subscribe to get new posts delivered instantly — never miss a tech share.

By submitting, you agree to receive emails. You can anytime.