orcarouter/ Qwen3.8-Flash-Next-Uncensored

16.1K 1 month ago

Qwen3.8-Flash-Next tensor-level abliterated— a latest Qwen4-architecture MoE (~177B total / ~6B active) with vision, reasoning, tool-calling, and 262K context. MLX 4/6/8-bit for Apple Silicon. Research use only.

vision tools thinking

4 models

Qwen3.8-Flash-Next-Uncensored:latest
47788aa6cde9 • 174GB • 256K context window •
Text, Image input • 1 month ago
Qwen3.8-Flash-Next-Uncensored:125b-a6b-mlx-4bit MLX
47788aa6cde9 • 174GB • 256K context window •
Text, Image input • 1 month ago
Qwen3.8-Flash-Next-Uncensored:125b-a6b-mlx-6bit MLX
7ef98b488040 • 206GB • 256K context window •
Text, Image input • 1 month ago
Qwen3.8-Flash-Next-Uncensored:125b-a6b-mlx-8bit MLX
6d1ef0d27226 • 237GB • 256K context window •
Text, Image input • 1 month ago