Check out the new frontier: five tiny, open‑weight LLMs that can call tools like a pro. Think NVIDIA‑level performance, smart function selection, and clean structured output—all in a compact package. Ready to power your domain‑specific AI? #OpenWeightModels #AgenticToolCalling #SmallLLMs
🔗
🔗
July 6, 2026 at 1:01 PM
Check out the new frontier: five tiny, open‑weight LLMs that can call tools like a pro. Think NVIDIA‑level performance, smart function selection, and clean structured output—all in a compact package. Ready to power your domain‑specific AI? #OpenWeightModels #AgenticToolCalling #SmallLLMs
🔗
🔗
Qwen 3.6 Impressions
Qwen 3.6 27b and 35b are great local AI models.
whyaiman.substack.com
May 4, 2026 at 4:15 PM
Evaluating #Gemma4 Family Of #AI Models
whyaiman.substack.com/p/evaluating...
LocalAI EnterpriseAI SmallLLMs AIStrategy AIEconomics
whyaiman.substack.com/p/evaluating...
LocalAI EnterpriseAI SmallLLMs AIStrategy AIEconomics
Evaluating Gemma4 Family Of Models
I finally got around to taking a look at Google's Gemma4 model(s).
whyaiman.substack.com
April 22, 2026 at 1:35 PM
Evaluating #Gemma4 Family Of #AI Models
whyaiman.substack.com/p/evaluating...
LocalAI EnterpriseAI SmallLLMs AIStrategy AIEconomics
whyaiman.substack.com/p/evaluating...
LocalAI EnterpriseAI SmallLLMs AIStrategy AIEconomics
Small LLMs Are the New Big Deal
Not every LLM needs 70B+ parameters.
In fact, small models are quietly taking over in 2025. Here’s why 👇
#SmallLLMs #EfficientAI
Not every LLM needs 70B+ parameters.
In fact, small models are quietly taking over in 2025. Here’s why 👇
#SmallLLMs #EfficientAI
apps.Post
May 7, 2025 at 3:41 AM
Small LLMs Are the New Big Deal
Not every LLM needs 70B+ parameters.
In fact, small models are quietly taking over in 2025. Here’s why 👇
#SmallLLMs #EfficientAI
Not every LLM needs 70B+ parameters.
In fact, small models are quietly taking over in 2025. Here’s why 👇
#SmallLLMs #EfficientAI