DEV Community

#ollama

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Qwen2.5 7B vs Qwen3 4B & 8B for Writing Correction: 60 Local Ollama Responses on Windows

Qwen2.5 7B vs Qwen3 4B & 8B for Writing Correction: 60 Local Ollama Responses on Windows

Comments
7 min read
Why I Stopped Chasing the Newest LLM (And What I Run Instead)

Why I Stopped Chasing the Newest LLM (And What I Run Instead)

1
Comments
6 min read
Flash Onyx 2.2: teaching a local model law and game feel

Flash Onyx 2.2: teaching a local model law and game feel

1
Comments
4 min read
I Replaced All My Cloud AI With Local Models — Here's What Actually Broke

I Replaced All My Cloud AI With Local Models — Here's What Actually Broke

Comments
6 min read
Your LLM Returns JSON That Isn't JSON: A Robust Structured-Output Pipeline for Local Models

Your LLM Returns JSON That Isn't JSON: A Robust Structured-Output Pipeline for Local Models

2
Comments
7 min read
Flash Onyx 2.1, one day later: my model spent 400 tokens thinking and returned an empty string

Flash Onyx 2.1, one day later: my model spent 400 tokens thinking and returned an empty string

Comments 1
6 min read
My inference server decided my second GPU no longer exists. Here is how I got it back without upgrading a driver.

My inference server decided my second GPU no longer exists. Here is how I got it back without upgrading a driver.

Comments
3 min read
Queried the Local Embeddings Store for the First Time

Queried the Local Embeddings Store for the First Time

Comments
2 min read
Fix Local LLM Quality: Context Stacking & Rope Freq Tweaks

Fix Local LLM Quality: Context Stacking & Rope Freq Tweaks

Comments
8 min read
How I Turned My Homelab Into an AI Content Factory (And Why I'm Not Stopping)

How I Turned My Homelab Into an AI Content Factory (And Why I'm Not Stopping)

Comments
6 min read
My AI quality gate scored 40 images. Humor: 7, forty times.

My AI quality gate scored 40 images. Humor: 7, forty times.

Comments
5 min read
Ornith-1.0 is a clever open coding model. Ollama's tool-calling isn't ready for it.

Ornith-1.0 is a clever open coding model. Ollama's tool-calling isn't ready for it.

Comments
4 min read
Moving Scheduled LLM Curation from Cloud APIs to Local Models

Moving Scheduled LLM Curation from Cloud APIs to Local Models

Comments
9 min read
Ollama v1 OpenAI Compat Drops Think Toggle

Ollama v1 OpenAI Compat Drops Think Toggle

Comments
2 min read
Nine ways to talk to a local model

Nine ways to talk to a local model

Comments
9 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.