Qwen3.8 27B

Qwen3.8 27B

Developer	Qwen
Release date	August 14, 2026
Family	Qwen
Generation	Qwen 3.8
Size class
Context window	1M tokens
Max output	236K tokens
Input	Text, image, video
Output	Text
Weights	Open weights
Predecessor	Qwen3.6 27B
Website	qwen.ai
Links	Model card Hugging Face

Part of a series on

input: $0.15
cached: $0.0375
output: $1.875
Context: 1Mtokens
Released: 3mo ago
Size: 27Bparameters

Specifications

Model

Developer: Qwen
Family: Qwen Qwen 3.8
Type: Language model
Released: August 14, 2026
Model ID: qwen/qwen3.8-27b

Capabilities

Input → output: Text, image, video → Text
Native context: 256K tokens
Max output: 236K tokens
Tokenizer: Qwen

Weights

Openness: Open weights
Size: 27B
Hugging Face: Qwen/Qwen3.8-27B

Lineage

Models built on this: Decider V1.3fine-tuned from
Decider V1.2fine-tuned from
Cleffine-tuned from
Ternary Bonsai 2 27Bvariant of

Sources:models.devOpenRouter

Metadata synced Nov 3, 2026, 11:17 PM UTC

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.