8 lines
251 B
Markdown
8 lines
251 B
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
---
|
||
|
|
|
||
|
|
# Qwen2.5-14B-Instruct-AWQ — offline inference bundle (v2)
|
||
|
|
|
||
|
|
AWQ 4-bit weights of Qwen2.5-14B-Instruct with a self-contained script.py (task-aware JSON harness) that runs fully offline (loads from `.`). Fits a 16 GB GPU.
|