alamios
/

QwQ-32B-DRAFT-0.5B-GGUF

Text Generation

Model card Files Files and versions

QwQ-32B-DRAFT-0.5B-GGUF

PREVIEW

Draft model for speculative decoding with Qwen/QwQ-32B, preview version.

Downloads last month: 6

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

Log In to add your hardware

4-bit

16-bit

Model tree for alamios/QwQ-32B-DRAFT-0.5B-GGUF

Base model

Qwen/Qwen2.5-0.5B

Quantized

(99)

this model

Collection including alamios/QwQ-32B-DRAFT-0.5B-GGUF

Draft GGUFs

4 items • Updated Mar 2 • 1