Spatial-SSRL-Qwen3VL-4B

internlm/Spatial-SSRL-Qwen3VL-4B

Image Text to Text4.8B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since October 20, 2026View on Hugging Face ↗
Downloads 30D
1,617
Total downloads
3,426
Gained 7D
—
Gained 30D
—
Likes
15
Rank · tracked models
#45,637
240(down 240 places)this week
Parameters
4.8B
Last source update
Apr 6, 2026
  • It moved from #4421 to #4459 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Spatial-SSRL-Qwen3VL-4B is a image text to text model published by internlm. OpenModelStats has tracked the model since Oct 20, 2026, most recently observing it Nov 18, 2026.

Published
Nov 21, 2025
Last updated
Apr 6, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
4,826,771,968
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsqwen3_vlimage-text-to-textmultimodalspatialsptial understandingself-supervised learningconversationalendataset:internlm/Spatial-SSRL-81karxiv:2510.27606

Publisher

internlmView publisher statistics →

Derived from Qwen/Qwen3-VL-4B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to Spatial-SSRL-Qwen3VL-4B
ModelDL 30D
Qwen3-VL-4B-Instruct-FP8Qwen173.7K
Qwen3-VL-4B-Instruct-AWQ-4bitcyankiwi4,628
EGM-4Bnvidia692
ZwZ-4BinclusionAI246
Qwen3-VL-4B-Thinking-AWQ-4bitcyankiwi141
Qwen3-VL-4B-Thinking-FP8Qwen825
internlm/Spatial-SSRL-Qwen3VL-4B — Downloads, Growth & Stats | OpenModelStats