Qwen3-4B-Thinking-2507-MLX-6bit

lmstudio-community/Qwen3-4B-Thinking-2507-MLX-6bit

Text Generation4B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 6, 2026View on Hugging Face ↗
Downloads 30D
43.8K
Total downloads
2.5M
Gained 7D
+12.2K(increase)
0.5%(up) vs baseline
Gained 30D
—
Likes
2
+0 in 7D
Rank · tracked models
#3,998
15(down 15 places)this week
Parameters
4B
Last source update
Aug 6, 2025
Momentum
59.1
  • Qwen3-4B-Thinking-2507-MLX-6bit gained 12.2K downloads during the last seven tracked days.
  • It moved from #895 to #897 among tracked Text Generation models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-4B-Thinking-2507-MLX-6bit is a text generation model published by lmstudio-community. OpenModelStats has tracked the model since Sep 6, 2026, most recently observing it Oct 6, 2026.

Published
Aug 6, 2025
Last updated
Aug 6, 2025
Library
transformers
License
apache-2.0
Task
Text Generation
Parameters
4,022,468,096
Spaces
—
Derivative models
—
Velocity 7D/day
1,746
transformerssafetensorsqwen3text-generationmlxconversationalbase_model:Qwen/Qwen3-4B-Thinking-2507base_model:quantized:Qwen/Qwen3-4B-Thinking-2507license:apache-2.0text-generation-inferenceendpoints_compatible6-bit

Publisher

lmstudio-communityView publisher statistics →

Derived from Qwen/Qwen3-4B-Thinking-2507 (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-4B-Thinking-2507-MLX-6bit
ModelDL 30D
Qwen3-4BQwen7.7M
Qwen3-4B-Instruct-2507Qwen3.6M
Qwen3-4B-BaseQwen617.3K
Qwen3-4B-Thinking-2507Qwen567.6K
Qwen3-4B-AWQQwen252.8K
qwen3-4b-base-dapo-v4ReliquaryForge148.5K
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-6bit — Downloads, Growth & Stats | OpenModelStats