Wicked-Stuff-31B-Final FP8-Dynamic (W8A8)
FP8 quantization of ReadyArt/Wicked-Stuff-31B-Final (Gemma 4 31B).
- Scheme:
FP8_DYNAMICW8A8: per-channel FP8 weights, dynamic per-token FP8 activations, on allLinearlayers (llm-compressor). Vision, audio, embeddings andlm_headstay BF16. No calibration data needed. - Hardware: Hopper (H100/H200) and Blackwell; Ada (RTX 4090/L40S) also has FP8.
vllm serve tacodevs/Wicked-Stuff-31B-Final-FP8-Dynamic --max-model-len 32768 --kv-cache-dtype fp8 \
--reasoning-parser gemma4 --enable-auto-tool-choice --tool-call-parser gemma4
Thinking: pass chat_template_kwargs: {"enable_thinking": true}.
- Downloads last month
- 18
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
Model tree for tacodevs/Wicked-Stuff-31B-Final-FP8-Dynamic
Base model
ReadyArt/gemma-4-31B-it-scotoma-2 Finetuned
ReadyArt/Wicked-Stuff-31B-Final