license: apache-2.0
pipeline_tag: text-generation
base_model: huihui-ai/Huihui-gemma-4-31B-it-abliterated
base_model_relation: quantized
tags:
- radiance
- amd
- rad2
Huihui Gemma 4 31B it Abliterated Radiance W4A8
Gemma 4 31B dense with W4A8 attention and feed-forward projections. The checkpoint is 20.40 GiB.
Verified for chat on two Radeon AI PRO R9700s as a secondary model alongside Qwen Flash Next. Use the chat endpoint with model: gemma4-31b-abliterated.
Build the executable and plugins together from the Radiance fork.
Download huihui-gemma4-31b-it-w4a8.rad and add this entry to the Radiance YAML configuration.
Adjust the model path to match your installation.
models:
gemma4-31b-abliterated:
model: /models/huihui-gemma4-31b-it-w4a8.rad
tp: 2
max-model-len: 8192
max-num-seqs: 2
max-num-batched-tokens: 512
num-speculative-tokens: 0
Verify the downloaded checkpoint against SHA256SUMS withsha256sum -c SHA256SUMS. License and attribution are in LICENSE and NOTICE.
The conversion uses the pinned source checkpoint.