Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix

QuantTrio/Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix

Text Generation534B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
158
Total downloads
6,902
Gained 7D
Gained 30D
Likes
7
Rank · tracked models
#31,616
602(down 602 places)this week
Parameters
534B
Last source update
Sep 5, 2025
  • It moved from #8333 to #8548 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-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix is a text generation model published by QuantTrio. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 13h ago.

Published
Jul 26, 2025
Last updated
Sep 5, 2025
Library
transformers
License
apache-2.0
Task
Text Generation
Parameters
534,148,150,784
Spaces
Derivative models
Velocity 7D/day
transformerssafetensorsqwen3_moetext-generationQwen3GPTQInt4-Int8Mix量化修复vLLMconversationalarxiv:2505.09388base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct

Publisher

QuantTrioView publisher statistics →

Derived from Qwen/Qwen3-Coder-480B-A35B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8Mix
ModelDL 30D
Inkling-MXFP4lightseekorg7,851
A.X-K1skt12.6K
MiMo-V2.5-Pro-FP4-DFlashXiaomiMiMo652
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16nvidia402.6K
NVIDIA-Nemotron-Labs-Teacher-Competition-Codingnvidia2,106
NVIDIA-Nemotron-Labs-Teacher-STEMnvidia1,780