lmstudio-ai / lmstudio-ai/docs

No local model is able to start a conversation in Bionic Omni Session.

Open
#248 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
MDX
Stars
172
Forks
128
Avg merge
8m
Merged PRs (30d)
1

Description

Whenever a message is sent to a local backend, the request fails immediately with the following error message:
Engine protocol ngPredictTokens request returned 400: {"error":{"code":400,"message":"Failed to initialize samplers: failed to parse grammar","type":"invalid_request_error"}}
This occurs regardless of the selected local model (tested with both Qwen 3.5 9B and Nemotron Nano 3 4B.

To Reproduce:
Launch Bionic Omni Session with the local engine connected.

Load any local model (e.g., Qwen 3.5 9B or Nemotron Nano 3B).

Type any basic prompt in the chat box (e.g., "why any local ai model not working" or "anything ").

Submit the prompt. The engine immediately returns a 400 grammar parsing error.
Image

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the failure in Bionic Omni Session with the local engine connected, using a local model such as Qwen 3.5 9B or Nemotron Nano 3 4B and a basic prompt. Start from the reported ngPredictTokens 400 response and its failed to parse grammar message. Done means a local model can start a conversation without this error.

Written by the indexing model from the issue text.

Assessment

Domain
ai, backend-api-design
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.