LLM
Qwen_Image-Q2_K.gguf-4bit
None|20000000000 parameters
A state-of-the-art 20B parameter multimodal image generation model from Qwen that excels in photorealistic image creation, multilingual text rendering, poster generation, typography, and instruction-following.
VARIANTS
0
formats available
SMALLEST
0 MB
best compressed
BEST ACCURACY
0%
top variant
DOWNLOADS
0
total
DOWNLOAD VARIANT
Qwen_Image-Q2_K.gguf-4bit
SELECT FORMAT
BENCHMARKS
USAGE
HARDWARE GUIDE
MODEL CARD
VARIANT COMPARISON
Accuracy vs. Size Tradeoff
Every variant is benchmarked against the FP16 baseline. Choose the right balance of accuracy and footprint for your workflow.
Benchmarks are performed on representative hardware. Accuracy is relative to model FP16 baseline.
| VARIANT | FORMAT | SIZE | PERPLEXITY | ACCURACY | LATENCY | BEST FOR | DOWNLOAD |
|---|---|---|---|---|---|---|---|
| FP16 (baseline) | — | 6570.00 MB | -- | 100% | — | Reference only | — |
ACCURACY RETENTION BY VARIANT (%)
FILE SIZE BY VARIANT (MB)
FP16 base6570.00 MB