Downloads · 30 days
5
5% of all-time downloads
dylanneve1/Qwen3.5-0.8B_int4_sym_group-1_dyn_stateful
Qwen3.5-0.8B_int4_sym_group-1_dyn_stateful is a machine learning model from dylanneve1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for openvino. The card lists the license as apache-2.0.
OpenVINO stateful model exported from Qwen/Qwen3.5-0.8B with INT4 symmetric channel-wise weight compression.
Downloads · 30 days
5
5% of all-time downloads
All-time downloads
93
Public
Repo size
895 MB
Likes
0
Public
Click a slice to open those files.
.bin875 MB · 97%
From the Hugging Face model README
OpenVINO stateful model exported from Qwen/Qwen3.5-0.8B with INT4 symmetric channel-wise weight compression.
| Property | Value |
|---|---|
| Base model | Qwen/Qwen3.5-0.8B |
| Architecture | Qwen3.5 (hybrid linear-attention + full-attention) |
| Weight format | INT4 (4-bit integer) |
| Quantization | Symmetric, channel-wise (group_size=-1) |
| Shapes | Dynamic |
| State management | Stateful (KV cache + conv/recurrent states) |
Qwen3.5 is a hybrid model with 24 layers: 18 linear-attention (GatedDeltaNet) + 6 full-attention layers in a 3:1 repeating pattern. Linear-attention layers use fixed-size conv and recurrent states (cache_params.past.{conv,ssm}.N).
pip install git+https://github.com/rkazants/optimum-intel.git@support_qwen3_5
pip install --pre -U openvino openvino-tokenizers nncf --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
pip install transformers==5.2.0
optimum-cli export openvino \
--model Qwen/Qwen3.5-0.8B \
--weight-format int4 \
--group-size -1 \
--sym \
Qwen3.5-0.8B_int4_sym_group-1_dyn_stateful