Tech Tactician

#

#Tag

#開源模型

Browse all articles tagged "開源模型"

24+ posts

🧪 64MB Ultra-Lightweight phonon-31m-en Beats Kokoro in Blind Test: Local AI Lab
On-Premise AI Lab
Mark Ku
·

🧪 64MB Ultra-Lightweight phonon-31m-en Beats Kokoro in Blind Test: Local AI Lab

🧪 M4 Pro Blazes Past 125 Tokens! Offline Coding Agent Model flint Debuts: Local AI Lab
On-Premise AI Lab
Mark Ku
·

🧪 M4 Pro Blazes Past 125 Tokens! Offline Coding Agent Model flint Debuts: Local AI Lab

🧪 66x KV Cache Savings! MemT-1.0-Nano Enables Local Native Long-Term Memory | Local AI Lab
On-Premises AI Lab
Mark Ku
·

🧪 66x KV Cache Savings! MemT-1.0-Nano Enables Local Native Long-Term Memory | Local AI Lab

🧪 Can 4B Parameters Control Thinking Budget? Pair with an 8-Step Distilled Image Gen Companion to Run Agents Offline: Local AI Lab
On-Premise AI Lab
Mark Ku
·

🧪 Can 4B Parameters Control Thinking Budget? Pair with an 8-Step Distilled Image Gen Companion to Run Agents Offline: Local AI Lab

🧪 GPU-Free and 15x Faster: 1.25M Parameter indra-ocr is a Local Savior | Local AI Lab
On-Premise AI Lab
Mark Ku
·

🧪 GPU-Free and 15x Faster: 1.25M Parameter indra-ocr is a Local Savior | Local AI Lab

🧪 322M beats 28B? convaiinnovations/laya claims to be 7.8x faster than the competition｜Local AI Lab
Local AI Lab
Mark Ku
·

🧪 322M beats 28B? convaiinnovations/laya claims to be 7.8x faster than the competition｜Local AI Lab

🧪 The most eye-popping download numbers this episode aren't a chat model, they're a decision LoRA: how GEV-26B-Decide lets the agent decide for itself whether to think more｜Local AI Lab
Local AI Lab
Mark Ku
·

🧪 The most eye-popping download numbers this episode aren't a chat model, they're a decision LoRA: how GEV-26B-Decide lets the agent decide for itself whether to think more｜Local AI Lab

🧪 The 740M embeddinggemma-2 handles text, images, video, and audio, and it even fits on your phone | Local AI Lab
Local AI Lab
Mark Ku
·

🧪 The 740M embeddinggemma-2 handles text, images, video, and audio, and it even fits on your phone | Local AI Lab

177B Model on a Diet: GSQ-RCO Quantized Version Matches Original with 2.2M Downloads
Local AI Lab
Mark Ku
·

177B Model on a Diet: GSQ-RCO Quantized Version Matches Original with 2.2M Downloads

🧪 164 MB, 174x Real-Time: Phonon-2 Makes Speech-to-Text Free From Cloud Taxes | Local AI Lab
Local AI Lab
Mark Ku
·

🧪 164 MB, 174x Real-Time: Phonon-2 Makes Speech-to-Text Free From Cloud Taxes | Local AI Lab

CLM-v0.1-8B doesn't generate text, only scores it: latency cut by up to 9x | Local AI Lab
Local AI Lab
Mark Ku
·

CLM-v0.1-8B doesn't generate text, only scores it: latency cut by up to 9x | Local AI Lab

🧪 Xiaomi's Flagship Needs 8 GPUs, But This MiMo-V2.6-Distill-Qwen-9B Runs with a Single Command | Local AI Lab
Local AI Lab
Mark Ku
·

🧪 Xiaomi's Flagship Needs 8 GPUs, But This MiMo-V2.6-Distill-Qwen-9B Runs with a Single Command | Local AI Lab

Categories

Browse articles by category

AI thumbnail
#1

AI

35+ articles

AI
DevOps thumbnail
#2

DevOps

32+ articles

DevOps
Frontend thumbnail
#3

Frontend

39+ articles

Frontend
Management thumbnail

Management

25+ articles

Management
Infra thumbnail

Infra

22+ articles

Infra
PowerShell thumbnail

PowerShell

15+ articles

PowerShell
Travel thumbnail

Travel

12+ articles

Travel
E-Commerce thumbnail

E-Commerce

11+ articles

E-Commerce
.NET Core thumbnail

.NET Core

11+ articles

.NET Core
Cloud thumbnail

Cloud

10+ articles

Cloud

標籤文章

🧪 64MB Ultra-Lightweight phonon-31m-en Beats Kokoro in Blind Test: Local AI Lab
On-Premise AI Lab

🧪 64MB Ultra-Lightweight phonon-31m-en Beats Kokoro in Blind Test: Local AI Lab

Mark Ku

·16 min read

🧪 M4 Pro Blazes Past 125 Tokens! Offline Coding Agent Model flint Debuts: Local AI Lab
On-Premise AI Lab

🧪 M4 Pro Blazes Past 125 Tokens! Offline Coding Agent Model flint Debuts: Local AI Lab

Mark Ku

·17 min read

🧪 66x KV Cache Savings! MemT-1.0-Nano Enables Local Native Long-Term Memory | Local AI Lab
On-Premises AI Lab

🧪 66x KV Cache Savings! MemT-1.0-Nano Enables Local Native Long-Term Memory | Local AI Lab

Mark Ku

·16 min read

🧪 Can 4B Parameters Control Thinking Budget? Pair with an 8-Step Distilled Image Gen Companion to Run Agents Offline: Local AI Lab
On-Premise AI Lab

🧪 Can 4B Parameters Control Thinking Budget? Pair with an 8-Step Distilled Image Gen Companion to Run Agents Offline: Local AI Lab

Mark Ku

·17 min read

🧪 GPU-Free and 15x Faster: 1.25M Parameter indra-ocr is a Local Savior | Local AI Lab
On-Premise AI Lab

🧪 GPU-Free and 15x Faster: 1.25M Parameter indra-ocr is a Local Savior | Local AI Lab

Mark Ku

·13 min read

🧪 322M beats 28B? convaiinnovations/laya claims to be 7.8x faster than the competition｜Local AI Lab
Local AI Lab

🧪 322M beats 28B? convaiinnovations/laya claims to be 7.8x faster than the competition｜Local AI Lab

Mark Ku

·22 min read

🧪 The most eye-popping download numbers this episode aren't a chat model, they're a decision LoRA: how GEV-26B-Decide lets the agent decide for itself whether to think more｜Local AI Lab
Local AI Lab

🧪 The most eye-popping download numbers this episode aren't a chat model, they're a decision LoRA: how GEV-26B-Decide lets the agent decide for itself whether to think more｜Local AI Lab

Mark Ku

·18 min read

🧪 The 740M embeddinggemma-2 handles text, images, video, and audio, and it even fits on your phone | Local AI Lab
Local AI Lab

🧪 The 740M embeddinggemma-2 handles text, images, video, and audio, and it even fits on your phone | Local AI Lab

Mark Ku

·20 min read

177B Model on a Diet: GSQ-RCO Quantized Version Matches Original with 2.2M Downloads
Local AI Lab

177B Model on a Diet: GSQ-RCO Quantized Version Matches Original with 2.2M Downloads

Mark Ku

·17 min read

🧪 164 MB, 174x Real-Time: Phonon-2 Makes Speech-to-Text Free From Cloud Taxes | Local AI Lab
Local AI Lab

🧪 164 MB, 174x Real-Time: Phonon-2 Makes Speech-to-Text Free From Cloud Taxes | Local AI Lab

Mark Ku

·17 min read

CLM-v0.1-8B doesn't generate text, only scores it: latency cut by up to 9x | Local AI Lab
Local AI Lab

CLM-v0.1-8B doesn't generate text, only scores it: latency cut by up to 9x | Local AI Lab

Mark Ku

·18 min read

🧪 Xiaomi's Flagship Needs 8 GPUs, But This MiMo-V2.6-Distill-Qwen-9B Runs with a Single Command | Local AI Lab
Local AI Lab

🧪 Xiaomi's Flagship Needs 8 GPUs, But This MiMo-V2.6-Distill-Qwen-9B Runs with a Single Command | Local AI Lab

Mark Ku

·20 min read

View more