Downloads · 30 days
7
15% of all-time downloads
Qwythos-9B-v2-int4-mtp-ov
Jeff98/Qwythos-9B-v2-int4-mtp-ov
Qwythos-9B-v2-int4-mtp-ov is a machine learning model from Jeff98. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
- Converted from https://huggingface.co/empero-ai/Qwythos-9B-v2 - MTP supported - int4 asym - Support intel GPU and CPU.
All-time downloads
47
Public
Repo size
6.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin6.3 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3_5
- Access
- Public
- Created
- Sep 18, 2026
- Updated
- Sep 19, 2026
- SHA
- 74d02d4e
Base models
Model card
From the Hugging Face model README
- Converted from https://huggingface.co/empero-ai/Qwythos-9B-v2
- MTP supported
- int4 asym
- Support intel GPU and CPU.
OVMS Requirement
This model uses the experimental/recent Qwen3.5 MTP speculative decoding path.
A recent OVMS development build is recommended and may be required. Older stable OVMS releases may not contain the necessary Qwen3.5 MTP support.
OVMS development builds are available at:
https://storage.openvinotoolkit.org/repositories/openvino_model_server/packages/weekly/
For bare-metal OVMS installation and deployment instructions, see:
https://docs.openvino.ai/2025/model-server/ovms_docs_deploying_server_baremetal.html
When troubleshooting MTP initialization issues, first update to the latest available weekly OVMS build before assuming the converted model is incompatible.
OVMS Deployment
ovms --rest_port 8000 \
--model_name Qwythos-9B-v2-int4-mtp-ov \
--model_path "path/to/model" \
--target_device GPU \
--draft_model_path . \ # Need this for MTP support
--enable_prefix_caching false # Need this for MTP support
Refer to https://huggingface.co/Jeff98/Qwen3.5-9B-uncensored-int4-ov for more details.
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en, zh
- Created
- Sep 18, 2026
- Updated
- Sep 19, 2026