  ollama launch claude --model gemma4:26b

▲ gcampos 3 hours ago | parent | next [-]

You need to increase the context window size or the tool calling feature wont work

	▲	mil22 2 hours ago \| parent [-]
		For those wondering how to do this: `OLLAMA_CONTEXT_LENGTH=64000 ollama serve` or if you're using the app, open the Ollama app's Settings dialog and adjust there. Codex also works: `ollama launch codex --model gemma4:26b`

▲ datadrivenangel 9 hours ago | parent | prev | next [-]

It's amazing how simple this is, and it just works if you have ollama and claude installed!

▲ pshirshov 7 hours ago | parent | prev [-]

For some reason, that doesn't work for me, claude never returns from some ill loop. Nemotron, glm and qwen 3.5 work just fine, gemma - doesn't.

▲ trvz 6 hours ago | parent [-]

Since that defaults to the q4 variant, try the q8 one:

  ollama launch claude --model gemma4:26b-a4b-it-q8_0

	▲	pshirshov 5 hours ago \| parent [-]
		Even tried gemma4:31b and gemma4:31b with 128k context (I have 72GiB VRAM). Nothing. I'm cursed I guess. That's ollama-rocm if that matters (I had weird bugs on Vulkan, maybe gemma misbehaves on radeons somehow?..). UPD: tried ollama-vulkan. It works, gemma4:31b-it-q8_0 with 64k context!