byteshape / image-text-to-text Open weights updated 1 month ago

Qwen3.8-27B-GGUF

Name: Qwen3.8-27B-GGUF
Author: byteshape

This is a GGUF-quantized version of Qwen3.8-27B produced with ByteShape's ShapeLearn, which learns the optimal datatype per tensor to maintain high quality even at very low bitlengths.

Params

27.0 B

Context

—

Downloads 30d

2.0 M

Likes

179

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

Download history

daily snapshots · 20 days

2.0 M833 K

Oct 5Oct 11Oct 18Oct 24

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-bf16.gguf	GGUF	0.9 GB	5.6 GB	✅ Runs comfortably
Qwen3.8-27B-IQ2_XXS-2.56bpw.gguf	IQ2_XXS	8.8 GB	14.3 GB	✅ Runs comfortably
Qwen3.8-27B-IQ3_XXS-2.88bpw.gguf	IQ3_XXS	9.9 GB	15.5 GB	✅ Runs comfortably
Qwen3.8-27B-IQ3_XS-3.01bpw.gguf	IQ3_XS	10.4 GB	15.9 GB	✅ Runs comfortably
Qwen3.8-27B-IQ3_S-3.23bpw.gguf	IQ3_S	11.0 GB	16.7 GB	✅ Runs comfortably
Qwen3.8-27B-IQ4_XS-3.84bpw.gguf	IQ4_XS	13.1 GB	18.9 GB	✅ Runs comfortably

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

Specifications

Parameters: 27.0 B
Licence: apache-2.0
First seen on the Hub: 2026-08-18
Base model: Qwen3.8-27B
Training datasets: undisclosed
Added to our catalog: 2026-10-05

Family

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

Base Qwen3.8-27B Qwen 7.7 M

Compare with any image-text-to-text model

Popular comparisons

gemma-4-26B-A4B-it 9.1 M gemma-4-31B-it 8.5 M Qwen3.8-27B 7.7 M Qwen3.8-27B-FP8 4.3 M Qwen3.6-35B-A3B 3.7 M Qwen3.6-35B-A3B-FP8 3.5 M