orcarouter/ Qwen3.8-Flash-Next-Uncensored:125b-a6b-mlx-8bit

18 3 hours 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
... /
params
ef498ab97953 · 109B
{
"min_p": 0,
"num_ctx": 262144,
"presence_penalty": 0,
"repeat_penalty": 1,
"temperature": 1,
"top_k": 20,
"top_p": 0.95
}