Qwen3.8-27B-FP8-Dynamic
FP8_DYNAMIC quantization of Qwen/Qwen3.8-27B, produced with llm-compressor.
Vision encoder, gated-delta attention (conv1d / linear_attn), lm_head, embeddings, and norm layers are kept in original precision.
- Downloads last month
- 28
Model tree for lokeshe09/Qwen3.8-27B-FP8-Dynamic
Base model
Qwen/Qwen3.8-27B