GLM-5.3-Flash-AWQ-W4A16-kda-w8-experimental

JJ48-24/GLM-5.3-Flash-AWQ-W4A16-kda-w8-experimental

Text Generation327B parametersLicense: mit
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
46
Total downloads
46
Gained 7D
+46(increase)
Gained 30D
—
Likes
0
+0 in 7D
Rank · tracked models
—
–this week
Parameters
327B
Last source update
Sep 16, 2026
  • GLM-5.3-Flash-AWQ-W4A16-kda-w8-experimental gained 46 downloads during the last seven tracked days.

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 2026-09-08. Charts appear as daily observations accumulate.

Overview

GLM-5.3-Flash-AWQ-W4A16-kda-w8-experimental is a text generation model published by JJ48-24. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it Sep 16, 2026.

Published
Sep 8, 2026
Last updated
Sep 16, 2026
Library
—
License
mit
Task
Text Generation
Parameters
327,440,948,062
Spaces
—
Derivative models
—
Velocity 7D/day
7
safetensorsglm5_nextcompressed-tensorssm80cmp-170hxvllmtext-generationconversationalbase_model:wtdcode/GLM-5.3-Flash-AWQ-W4A16base_model:quantized:wtdcode/GLM-5.3-Flash-AWQ-W4A16license:mitregion:us

Publisher

JJ48-24View publisher statistics →

Derived from wtdcode/GLM-5.3-Flash-AWQ-W4A16 (reported by the source; parent not yet tracked).

Similar models

Models similar to GLM-5.3-Flash-AWQ-W4A16-kda-w8-experimental
ModelDL 30D
DSV4.1-Flash-SAGE-EXL3-3.30bpwvcruz305787
DeepSeek-V4-Flash-0731-MLX-Serve-mixed-2-3-8bitddalcu1,857
GLM-5.3-Flash-Uncensored-FP8orcarouter151.8K
GLM-5.3-Flash-CYBERSECURITY-W4A16dealignai6,775
GLM-5.3-Flash-UNCENSORED-W4A16dealignai4,022
GLM-5.3-FlashAMAImedia3,869