Skip to content

llmtech: rename model to nvidia/Qwen3.8-27B-NVFP4 - #7549

Open
Pessimist228 wants to merge 2 commits into
anomalyco:devfrom
Pessimist228:llmtech-model-id-nvidia
Open

Pessimist228 wants to merge 2 commits into
anomalyco:devfrom
Pessimist228:llmtech-model-id-nvidia

Conversation

@Pessimist228

Copy link
Copy Markdown
Contributor

The build LLM Tech serves is NVIDIA's own NVFP4 checkpoint of Qwen3.8-27B, not the community one, so the canonical model id is now nvidia/Qwen3.8-27B-NVFP4.

This moves providers/llmtech/models/unsloth/Qwen3.8-27B-NVFP4.toml to providers/llmtech/models/nvidia/Qwen3.8-27B-NVFP4.toml. Nothing else changes: same endpoint, same pricing, same reasoning options.

The previous id unsloth/Qwen3.8-27B-NVFP4 is still accepted by the API as a hidden synonym and will keep working, so anyone holding the old id in a config is not broken by this rename.

Live catalogue: https://api.llmtech.eu/v1/models

The served build is NVIDIA's own NVFP4 checkpoint, not the community one.
The previous id stays accepted by the API as a synonym, so nothing breaks
for anyone who has not switched yet.
@github-actions

Copy link
Copy Markdown
Contributor

No actionable findings.

@github-actions github-actions Bot added the reviewer: ready Automated review found no actionable items label Sep 20, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

reviewer: ready Automated review found no actionable items

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant