This model is a distilled version of Qwen/Qwen3-30B-A3B-Instruct designed to inherit the reasoning and behavioral characteristics of its much larger teacher model, deepseek-ai/DeepSeek-V3.1.
2,109 Pulls 2 Tags Updated 10 months ago
This repo contains both the Q4_K_XL version of Qwen3-30B-A3B-Instruct-2507 and Qwen3-30B-A3B-Thinking-2507
1,072 Pulls 3 Tags Updated 11 months ago
Unsloth Dynamic 2.0 Quants achieves superior accuracy & SOTA quantization performance. UD-Q4_K_XL provided.
1,001 Pulls 2 Tags Updated 11 months ago
203 Pulls 1 Tag Updated 11 months ago