lmstudio-community/Qwen3-VL-4B-Instruct-GGUF

Hugging Face model.

Current status

No changes detected since 30 Oct 2025

Licence: Apache-2.0
Remote code: No
Access: Public
Repository: https://huggingface.co/lmstudio-community/Qwen3-VL-4B-Instruct-GGUF (opens in a new tab)
Last checked: 04 Nov 2026, 10:36 UTC
History tracked since: 30 Oct 2025

30 Oct 2025
- Weights changed
  
  New model weights detected.
  
  Weights Severity: Critical
  - New weights file: Qwen3-VL-4B-Instruct-Q8_0.gguf
  Recorded change
  1 added: Qwen3-VL-4B-Instruct-Q8_0.gguf
  
  Revisions
  9f8bfcb → 9eaf998
  
  Commit history on Hugging Face Files at 9eaf998
- Weights changed
  
  New model weights detected.
  
  Weights Severity: Critical
  - New weights file: Qwen3-VL-4B-Instruct-Q6_K.gguf
  Recorded change
  1 added: Qwen3-VL-4B-Instruct-Q6_K.gguf
  
  Revisions
  296510c → 9f8bfcb
  
  Commit history on Hugging Face Files at 9f8bfcb
- Weights changed
  
  New model weights detected.
  
  Weights Severity: Critical
  - New weights file: Qwen3-VL-4B-Instruct-Q4_K_M.gguf
  Recorded change
  1 added: Qwen3-VL-4B-Instruct-Q4_K_M.gguf
  
  Revisions
  b10378a → 296510c
  
  Commit history on Hugging Face Files at 296510c
- Weights changed
  
  New model weights detected.
  
  Weights Severity: Critical
  - New weights file: mmproj-Qwen3-VL-4B-Instruct-F16.gguf
  Recorded change
  1 added: mmproj-Qwen3-VL-4B-Instruct-F16.gguf
  
  Revisions
  ce19921 → b10378a
  
  Commit history on Hugging Face Files at b10378a

Compare two stored snapshots to see what changed in licence, weights, configuration, access and the model card.

Explore the evidence behind each change, including file diffs, model card content and metadata.