Downloads · 30 days
0
niefeng/eelml-qwen3-5-0-8b-mlx-q4
eelml-qwen3-5-0-8b-mlx-q4 is a machine learning model from niefeng. 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.
EELML Studio runtime-ready package compiled from Qwen/Qwen3.5-0.8B.
Downloads · 30 days
0
Access
Public
Updated Aug 21, 2026
Repo size
444 MB
Likes
0
Public
Click a slice to open those files.
.eelml444 MB · 100%
From the Hugging Face model README
EELML Studio runtime-ready package compiled from
Qwen/Qwen3.5-0.8B.
This is a complete EELML graph-v3 physical package. Quantization, tensor
reordering, alignment, and the target MLX layout are completed offline. The
production runtime consumes only the .eelml package and does not fall back to
Safetensors, GGUF, or another graph.
| Field | Value |
|---|---|
| File | qwen3.5-0.8b-official-mlx-q4-runtime2.eelml |
| Package ID | qwen3.5-0.8b-official-mlx-q4-runtime2 |
| Package version | 2.0.0 |
| Canonical graph | qwen3_5.canonical@3 |
| Physical layout | mlx_qwen3_5_q4_v1 |
| Runtime adapter | mlx_qwen3_5@2 |
| Protocol adapter | qwen35-native-tool-v1@1 |
| Chat template | qwen35-chatml-v1 |
| Tool protocol | qwen35-xml-tool-v1 |
| Size | 444,184,075 bytes |
| SHA-256 | e443521cc4142f77aea167be64a876974bfb9bd716395b96059345936026067b |
Install this model from EELML Studio's model manager. The App verifies the single-file package and commits the admitted model identity to SQLite only after the package, runtime, and protocol contracts agree.
The upstream Qwen3.5 0.8B model is published by Alibaba Cloud under Apache License 2.0. The EELML physical package remains subject to the upstream model license and attribution requirements.
这是 Qwen3.5 0.8B 的 EELML Runtime 2.0 正式包。它只允许由 mlx_qwen3_5@2
执行,禁止由文件名推测模型身份,也禁止不兼容 Runtime 或协议静默回退。