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
Safetensors
Model size
28B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lokeshe09/Qwen3.8-27B-FP8-Dynamic

Base model

Qwen/Qwen3.8-27B
Quantized
(423)
this model