DisOOM/Qwen1.5-22B-Chat-Merge-GGUF · Hugging Face

Edit model card

I got broken models when use the k quantize so there's no k quantized models(sad)

Downloads last month: 67

GGUF

Model size

22B params

Architecture

qwen2

4-bit

5-bit

8-bit

Inference Examples

Text Generation

Inference API (serverless) has been turned off for this model.