unsloth / text-to-image updated 6 months ago

Qwen-Image-2512-GGUF

Name: Qwen-Image-2512-GGUF
Author: unsloth

This is a GGUF quantized version of Qwen-Image-2512. unsloth/Qwen-Image-2512-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance.

Params

—

Context

—

Downloads 30d

77 K

Likes

393

Commercial use: allowed apache-2.0 Not gated GGUF 2 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

80 K77 K

Jul 28Jul 31Aug 3Aug 6

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
qwen-image-2512-Q2_K.gguf	Q2_K	7.3 GB	8.6 GB	✅ Runs comfortably
qwen-image-2512-Q3_K_S.gguf	Q3_K_S	9.2 GB	10.6 GB	✅ Runs comfortably
qwen-image-2512-Q3_K_M.gguf	Q3_K_M	9.9 GB	11.4 GB	✅ Runs comfortably
qwen-image-2512-Q4_0.gguf	Q4_0	11.9 GB	13.5 GB	✅ Runs comfortably
qwen-image-2512-Q4_K_S.gguf	Q4_K_S	12.3 GB	14.0 GB	✅ Runs comfortably
qwen-image-2512-Q4_1.gguf	Q4_1	12.8 GB	14.6 GB	✅ Runs comfortably
qwen-image-2512-Q4_K_M.gguf	Q4_K_M	13.2 GB	15.1 GB	✅ Runs comfortably
qwen-image-2512-BF16.gguf	GGUF	40.9 GB	45.5 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Base model and the most-downloaded derivatives in the catalog.

Compare with

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB