Saluki 27B : This AI Model Is Built for Agents BUT 7x Smaller Than Qwen 3.8 27B
Long-form6:18Education2.7× channel median
Published Oct 13, 2026, 12:40 PM · 4d ago
Codedigipt
15.7K subscribers · median 1.9K views
Screen recording · confirmed$Likely
Views
5,159
+7 views/hour
Likes
44
0.9% of views
Comments
1
0.02% of views
Checked every 3 h while the video is this age · last check 14h ago · next in 0 min. YouTube itself updates public counts with a short delay.
Views / hour now
7
measured 14h ago
Peak views / hour
7
14h ago
Avg views / day
1.1K
since upload
First 24 hours
—
not tracked from upload
vs channel median
2.7×
Rank in channel
#6
of 20 tracked
Engagement
0.9%
likes + comments / views
Est. ad revenue
$36–$83
lifetime, $7–16 RPM
Views over time
3 readings · line: total views · bars: views gained per hour
Description
Meet Saluki 27B, a highly compressed AI model that fits into just 7.89GB! Discover how 2-bit quantization makes this powerful model smaller, its tool-calling and AI agent capabilities, benchmark results, and whether you can run it locally on your own PC.
================================
Subscribe 2nd channel here: https://www.youtube.com/@AIPhyOx
================================
=============================================
Follow on twitter : https://x.com/Codedigipt
Follow Codedigipt channel on WhatsApp: https://whatsapp.com/channel/0029Vb8SzEP89inlpgnxKE2i
========= Resources =========================
https://huggingface.co/ConwayResearch/Underdog-Saluki-27B-1.0
=============================================
#OpenSourceAI #aicoding #aiagents #artificialintelligence #chatgpt #claudecode #automation #aitools #productivity #technews #ai2026
Disclaimer:
The content in this video is for informational and educational purposes only. All opinions expressed are my own. I am not a licensed professional, and this video should not be considered professional advice. Performance benchmarks are based on specific tests and may not reflect all use cases. Always do your own research and consult with a qualified expert where necessary.
Use the information provided at your own risk.
Some links or products mentioned may be affiliate links, which means I may earn a small commission at no extra cost to you. Thank you for your support!
Tags
Saluki AISaluki 27BUnderdog AIAI modelsopen source AIlocal AIsmall language modelsLLM2-bit quantizationAI agentstool callinglocal LLMrun AI locallyQwen3.8 27Bllama.cppquantized AI modelsAI benchmarksAI coding assistantOllamaAI newsAIPhyOx
Details
- Published
- Oct 13, 2026, 12:40 PM
- Length
- 6:18 (378 s)
- Format
- Long-form
- Category
- Education
- Audio language
- EN
- Quality
- HD
- Captions
- No
- Made for kids
- No
- Licensed content
- Yes
- Video ID
- L3aeM9ShQUc
More from Codedigipt
Nemotron 3.5 Bolt 74B : NVIDIA New Open Source model Made Local AI Better482 views · 21h ago · +36/h
Reflection Beam 1.0 : A New Open Weight AI Model1.2K views · 1d ago
Nemotron 3.5 Super VL — NVIDIA’s New AI Model Is Built for Multimodal Autonomous Agents1.5K views · 1d ago
LFM2.5 24B A2B - This Tiny Compute AI Model Is Seriously Impressive1.8K views · 2d ago · +8/h
Cat Jam (stealth model) Is built for agentic coding & very fast8.8K views · 3d ago · +44/h
MiniCPM V 4.7 - This Open Source AI Model Might Surprise You3K views · 3d ago · +4/h
Andrej Karpathy Reveals the HUGE Gap in AI Understanding1.4K views · 4d ago
EmbeddingGemma 2 — Google’s New 740M AI Model Is Surprisingly Powerful1.2K views · 5d ago · +1/h
Statistics from the YouTube Data API, tracked by FameX. Views per hour, revenue and comparisons are FameX estimates.