Skip to content

bjk110

Qwen3.5-122B-A10B-abliterix-FP8

bjk110/Qwen3.5-122B-A10B-abliterix-FP8

Qwen3.5-122B-A10B-abliterix-FP8 is a text generation model from bjk110. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.

FP8 W8A8 quantization of wangzhang/Qwen3.5-122B-A10B-abliterix — the 122B/A10B abliterated (uncensored) Qwen3.5 MoE — packaged for vLLM serving on NVIDIA Blackwell hardware (DGX Spark GB10 / SM121).

Downloads · 30 days

32

8% of all-time downloads

All-time downloads

422

Public

Parameters

122B

124 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors124 GB · 100%

Parameter types

How the weights are stored.

F8_E4M3121B · 99%

Try a prompt

Base models

Task
Text Generation
Type
qwen3_5_moe_text
License
apache-2.0
Created
May 19, 2026
Updated
May 19, 2026