Qwen3-235B-A22B-Instruct-2507-BitsMoE-1.6bit

zjiayu064/Qwen3-235B-A22B-Instruct-2507-BitsMoE-1.6bit

Text Generation21.5B parametersLicense: apache-2.0
Tracked by OpenModelStats since October 4, 2026View on Hugging Face ↗
Downloads 30D
468
Total downloads
468
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
#43,594
376(down 376 places)this week
Parameters
21.5B
Last source update
Oct 4, 2026
  • It moved from #12475 to #12565 among tracked Text Generation models this week.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-235B-A22B-Instruct-2507-BitsMoE-1.6bit is a text generation model published by zjiayu064. OpenModelStats has tracked the model since Oct 4, 2026, most recently observing it Oct 4, 2026.

Published
Oct 3, 2026
Last updated
Oct 4, 2026
Library
—
License
apache-2.0
Task
Text Generation
Parameters
21,527,172,311
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsqwen3_moebitsmoemoequantized1.6bitconversationaltext-generationarxiv:2606.00079base_model:Qwen/Qwen3-235B-A22B-Instruct-2507base_model:quantized:Qwen/Qwen3-235B-A22B-Instruct-2507license:apache-2.0

Publisher

zjiayu064View publisher statistics →

Derived from Qwen/Qwen3-235B-A22B-Instruct-2507 (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-235B-A22B-Instruct-2507-BitsMoE-1.6bit
ModelDL 30D
gpt-oss-20b-RichardErkhov-heresyMuXodious113.9K
gpt-oss-safeguard-20bopenai36.6K
gpt-oss-20bRedHatAI3,449
SmallThinker-21BA3B-InstructTiiny658
Ornith-1.5-35B-A3B-FULL-OBLITERATED-NVFP4jhone888749
Nex-N2.5-mini-mixed-NVFP4-FP8primitive-ai707