ISTA-DASLab / image-text-to-text Open weights updated 2 months ago

Qwen3.8-27B-GSQ-RCO-GGUF

Name: Qwen3.8-27B-GSQ-RCO-GGUF
Author: ISTA-DASLab

.json, run python tools/makeplots.py tools/results/.json then paste the printed Markdown table into "Results". The header (banner + badges) is shared across all releases. NB: the YAML block must remain the very first bytes of the file (HF requirement). -->

Params

—

Context

—

Downloads 30d

1.4 M

Likes

2,608

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

Download history

daily snapshots · 56 days

▲ 128 K in the last 30 days (8.6%)

1.7 M885 K

Sep 16Oct 4Oct 23Nov 10

Can you run it?

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
mmproj-Qwen3.8-27B-BF16.gguf	GGUF	0.9 GB	1.5 GB	✅ Runs comfortably
Qwen3.8-27B-GSQ-RCO-IQ2_XS-mtp.gguf	IQ2_XS	8.8 GB	10.1 GB	✅ Runs comfortably
Qwen3.8-27B-GSQ-RCO-IQ2_S-mtp.gguf	IQ2_S	9.6 GB	11.1 GB	✅ Runs comfortably
Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp.gguf	IQ3_XXS	10.4 GB	12.0 GB	✅ Runs comfortably
Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp.gguf	IQ3_S	12.1 GB	13.8 GB	✅ Runs comfortably

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

Specifications

Licence: apache-2.0
First seen on the Hub: 2026-08-28
Base model: Qwen3.8-27B
Training datasets: undisclosed
Added to our catalog: 2026-09-16

Family

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

Base Qwen3.8-27B Qwen 7.5 M

Compare with any image-text-to-text model

Popular comparisons

Florence-2-base 11.7 M Qwen3.8-27B 7.5 M Qwen3-VL-8B-Instruct 7.1 M gemma-4-31B-it 7.1 M Qwen3.8-Flash-Next-GSQ-RCO-GGUF 6.8 M GLM-5.3-Flash 6.4 M