Ollama - Local LLMs for everyone!

405 readers

1 users here now

A place to discuss Ollama, from basic use, extensions and addons, integrations, and using it in custom code to create agents.

founded 1 year ago

MODERATORS

catty@lemmy.world

ollama model for OpenClaw (lemmy.world)

submitted 5 months ago by Pulsar@lemmy.world to c/Ollama@lemmy.world

4 comments fedilink hide all child comments

What are the best Ollama models for OpenClaw? The best is defined as to be able to understand OpenClaw tools.

top 4 comments

sorted by: hot top controversial new old

[–] hohoho@lemmy.world 4 points 5 months ago (1 children)

Qwen3.5 and gpt-oss are good for local inference with tool use capabilities.

[–] Pulsar@lemmy.world 2 points 4 months ago (1 children)

I tried Qwen3.5 9b & 4b versions for the last couple of days and my experience has been really bad. Qwen3.5 regardless the size are slow and seems like overthinking too much. I'm getting better results with ministral-3.

[–] hohoho@lemmy.world 1 points 4 months ago

I’ve had decent results with Qwen3.5-122B-A10B-AWQ-4bit. But I’m planning to try the latest unsloth version to see how it performs. There are times when I think I’m talking to a child especially when I come off of using Opus.

[–] Pulsar@lemmy.world 1 points 4 months ago

I switched from Ollama to Lemonade-server and got Qwen3.5-9B-GGUF working great.