qwen3.5-4b-16k-grpo-reasoninggym-restedmarlin-s300

budget-internalization-iclr2027/qwen3.5-4b-16k-grpo-reasoninggym-restedmarlin-s300

Image Text to Text4.7B parameterstransformersLicense: apache-2.0

Tracked by OpenModelStats since September 25, 2026View on Hugging Face ↗

Downloads 30D: 15
Total downloads: 15
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: —; –this week
Parameters: 4.7B
Last source update: Sep 25, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-25. Charts appear as daily observations accumulate.

Overview

qwen3.5-4b-16k-grpo-reasoninggym-restedmarlin-s300 is a image text to text model published by budget-internalization-iclr2027. OpenModelStats has tracked the model since Sep 25, 2026, most recently observing it Sep 26, 2026.

Published: Sep 25, 2026
Last updated: Sep 25, 2026
Library: transformers
License: apache-2.0
Task: Image Text to Text
Parameters: 4,659,865,088
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorsqwen3_5image-text-to-textreasoningreasoning-gymgrporeinforcement-learningtoken-budgetconversationalbase_model:Qwen/Qwen3.5-4Bbase_model:finetune:Qwen/Qwen3.5-4B

Publisher

budget-internalization-iclr2027View publisher statistics →

Derived from Qwen/Qwen3.5-4B (reported by the source; parent not yet tracked).

Similar models

Models similar to qwen3.5-4b-16k-grpo-reasoninggym-restedmarlin-s300
Model	Task	DL 30D	Likes	Params
Qwen3.5-4BQwen	Image Text to Text	8M	1,013	4.7B
Qwen3.5-4B-BaseQwen	Image Text to Text	630.2K	106	4.7B
Qwen3.5-4B-AWQQuantTrio	Image Text to Text	217.6K	10	4.7B
Qwen3.5-4Bunsloth	Image Text to Text	116.5K	28	4.7B
Qwen3.5-4Bhamishivi	Image Text to Text	78.4K	0	4.7B
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2Jackrong	Image Text to Text	2,562	16	4.7B