Sign up

ProCreations/grug-v1.1-qwen-3.8-27b-fp8

🤗 Hugging Face sourceimage-text-to-textapache-2.026.9B params30 GBsafetensors✓ HF checksums availableupdated today
No torrent yet →

Grug v1.1 Qwen3.8 27B — FP8

vLLM-oriented quantization of ProCreations/grug-v1.1-qwen-3.8-27b, pinned to revision 3ab073b4bb06dc8a83e819a33485469f32b945ba. FP8 E4M3 with 128×128 block-scaled weights and dynamic activations. The vision tower, embeddings, LM head, GatedDeltaNet a/b gates, and MTP namespace are excluded from quantization.

The trained MTP head is not included in this repository. Use the corresponding -mtp-... repository for speculative decoding.

Serve

vllm serve ProCreations/grug-v1.1-qwen-3.8-27b-fp8 --max-model-len 32768 \
  --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder

The exact build script and structural report are included under reproduce/ and quantization_report.json.