AImodelsComparison.com 1,040 models
Menu
Models Best of Trending Can I run it? Methodology About
Qwen / image-text-to-text updated 3 weeks ago

Qwen3.8-27B

--- libraryname: transformers license: apache-2.0 pipelinetag: image-text-to-text ---

Params
27.8 B
Context
—
Downloads 30d
6.7 M
Likes
14,397
Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 21 days
6.7 M1.0 M
Aug 20Aug 27Sep 3Sep 9

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 55.6 GB 65.8 GB ❌ Won’t fit
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
Qwen3_5ForConditionalGeneration
Parameters
27.8 B
Tensor type
BF16
Licence
apache-2.0
First seen on the Hub
2026-08-05
Training datasets
undisclosed
Added to our catalog
2026-08-20

Family

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

Derivative Qwen3.8-27B-FP8 Qwen 7.0 M Derivative Qwen3.8-27B-MLX-4bit lmstudio-community 4.0 M Derivative Qwen3.8-27B-MLX-8bit lmstudio-community 3.7 M Derivative Qwen3.8-27B-MLX-6bit lmstudio-community 3.7 M Derivative Qwen3.8-27B-MLX-5bit lmstudio-community 3.6 M
Compare with
Qwen3.6-35B-A3B-FP8 12.4 M gemma-4-31B-it 8.7 M gemma-4-26B-A4B-it 8.6 M Qwen3.6-27B-FP8 7.2 M Qwen3.8-27B-FP8 7.0 M Qwen3.6-27B 4.9 M
Appears in
Best open coding models Commercial-use text models Models that fit in 12 GB
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.