lmstudio-ai / lmstudio-ai/lmstudio-bug-tracker

Failed to generate with qwen2.5-vl bf16 models

Open
#562 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
No language data
Stars
152
Forks
38
PR merge metrics
No merged PRs in 30d

Description

**Which version of LM Studio?**
0.3.14 build 5

**Which operating system?**
macOS 15
M2 Max with 32G RAM

**What is the bug?**
I downloaded the qwen2.5-vl-3B-instruct-bf16 model and try to deploy it.
It keeps generating for a very long time and could not get any response. The GPU usage is always 100%.
I'm sure that I have enough RAM or VRAM to load this model.
Running a 8bit model is OK.

**Screenshots**
Image

**Logs**
No any error logs

**To Reproduce**
Steps to reproduce the behavior:
1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Contributor guide

No contributing guide indexed for this repository

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

No source files or tests are named. Start by reproducing the issue in LM Studio 0.3.14 build 5 on macOS 15 with the qwen2.5-vl-3B-instruct-bf16 model, then compare it with the working 8-bit model and capture useful logs. Done means the bf16 model generates a response or the limitation is documented with actionable diagnostics.

Written by the indexing model from the issue text.

Assessment

Tech stack
macos
Domain
desktop, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.