Modeldex
Qwen

Qwen3.8-27B

SIZE28B
82Quality
Vision
TextImageDownloads7.7M/mo
TextLikes18K

Vision-language model from Qwen, 28B parameters.

Open weightsApache 2.0966/1040
Drag to turnCard front showing

QwenTextPromo

Qwen3.8-27B

Vision-language model from Qwen, 28B parameters.

Qwen/Qwen3.8-27B
Type
Text
Quality
82 · Top 18% on the Epoch Capabilities Index
Parameters
28B (27,781,427,952)
Downloads
7.7M in the last 30 days
Likes
18K
Access to weights
Open download
On Hugging Face since
Aug 5, 2026
Takes in
Text, Image
Puts out
Text
Access
Open weights
License
Apache 2.0
Rarity
Promo
Set number
966/1040

License read from the model’s Hugging Face card. Stats from Qwen’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for Qwen3.8-27B, refreshed daily from Epoch AI and LMArena.

Top 18% of the 277 models on the Epoch Capabilities Index: #52.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

46 providers sell Qwen3.8-27B through an API, and 5 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
AMDFreeQwen3.8-27BFreeFree131K
HetznerFreeQwen3.8-27BFreeFree262K
IteraComputeFreeqwen/qwen3.8-27bFreeFree131K
engyCheapest paidqwen3.8-27b$0.045$0.321M
DevPass (LLM Gateway)Qwen3.8-27B$0.08$0.35262K
LLM Gatewayconsensusprotocol/Qwen3.8-27B$0.08$0.35262K
Cortecsqwen3.8-27b$0.10$0.401M
RunInfraQwen/Qwen3.8-27B$0.10$0.40262K
EmpirioLabs AIqwen3-8-27b$0.17$0.50262K
NanoGPTqwen/qwen3.8-27b$0.15$0.701M
Show 36 more providers
ProviderInputOutputContext
Vultrqwen3.8-27b$0.15$1.00262K
NEAR AI CloudQwen/Qwen3.8-27B$0.04$1.35262K
Cerebrasqwen-3.8-27b$0.99$1.49131K
Tempr Gatewaycerebras/qwen-3.8-27b$0.99$1.49131K
CrofAIqwen3.8-27b$0.20$1.50262K
Ofoxqwen/qwen3.8-27b$0.50$1.711.13M
LLM Technvidia/Qwen3.8-27B-NVFP4$0.25$2.09262K
OpenRouterqwen/qwen3.8-27b$0.24$2.201M
AKI.IOqwen3.8-27b$0.30$2.20262K
Kosmik Computeqwen/qwen3.8-27b$0.35$2.20262K
OrcaRouterqwen/qwen3.8-27b$0.33$2.40262K
TensorXqwen/qwen3.8-27b$0.40$2.40262K
Regolo AIqwen3.8-27b$0.58$2.42120K
Deep InfraQwen/Qwen3.8-27B$0.20$2.50262K
Kilo Gatewayqwen/qwen3.8-27b$0.42$2.55262K
Standard Computeqwen/qwen3.8-27b$0.42$2.55262K
ai&qwen/qwen3.8-27b$0.40$3.00262K
CommandCodeQwen/Qwen3.8-27B$0.40$3.00262K
CoreWeaveQwen/Qwen3.8-27B$0.40$3.00262K
Novita AIqwen/qwen3.8-27b$0.42$3.001M
Nebius Token FactoryQwen/Qwen3.8-27B$0.45$3.00262K
Charm Hyperqwen3.8-27b$0.50$3.001M
Eden AIqwen/qwen3.8-27b$0.50$3.001M
Vercel AI Gatewayalibaba/qwen3.8-27b$0.50$3.001M
Opperqwen3.8-27b$0.58$3.00262K
OVHcloud AI Endpointsqwen3.8-27b$0.47$3.19262K
Ambientqwen/qwen3.8-27b$0.32$3.2033K
Cloudflare Workers AI@cf/qwen/qwen3.8-27b$0.45$3.20262K
Neuralwattqwen-3.8-27b$0.45$3.20262K
Venice AIqwen-3-8-27b$0.45$3.20262K
Berget.AIQwen/Qwen3.8-27B-FP8$0.46$3.48262K
evrocQwen/Qwen3.8-27B$0.87$3.50262K
Scalewayqwen3.8-27b$0.68$3.76262K
Groqqwen/qwen3.8-27b$0.80$4.00131K
AI/ML APIalibaba/qwen3.8-27b$0.62$4.40262K
Blue ClawQwen3.8-27B——131K

Hugging Face Inference Providers

HostInputOutputContextSpeedFirst token
CerebrasFastestTools$0.99$1.4966K532 tok/s0.2s
DeepInfraTools$0.20$2.50262K13 tok/s1.0s
NovitaTools$0.42$3.001M35 tok/s1.1s
OVHcloudTools$0.47$3.19262K65 tok/s0.5s
Featherless—————

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

More from Qwen

Qwen

Qwen-Image-2.1-Turbo

SIZE7.1B
New
Image generation
TextDownloads23K/mo
ImageLikes970

Text-to-image model from Qwen, 7.1B parameters.

Open weightsQwen Research license1031/1040
Qwen

Qwen3.8 Omni Flash

CTX1M
Reasoning · Vision · Tools
TextImageAudioVideoInput$0.15/M
TextOutput$0.47/M

Qwen omni model for text, vision, audio, and multimodal agent tasks

PaidProprietary1009/1040
Qwen

Qwen-Image-2.1

SIZE7.1B
78Quality
Image generation
TextDownloads180K/mo
ImageLikes3.4K

Text-to-image model from Qwen, 7.1B parameters.

Open weightsQwen Research license1004/1040
Qwen

Qwen3.8 Flash

CTX1M
Reasoning · Vision · Tools
TextImageVideoInput$0.15/M
TextOutput$0.47/M

Qwen vision-language model for visual reasoning, documents, and agent tasks

PaidProprietary989/1040
Qwen

Qwen3.8-Flash-Next

SIZE180B
87Quality
Vision
TextImageDownloads2.5M/mo
TextLikes6.3K

Vision-language model from Qwen, 180B parameters.

Open weightsQwen Community 1.0 license984/1040
Qwen

Qwen3.8-2.4T-A95B

SIZE2.4T
Text
TextDownloads26K/mo
TextLikes1.3K

Language model from Qwen, 2.4T parameters.

Open weightsQwen3.8 Max license971/1040
Qwen

Qwen3.8 Max

CTX1M
93Quality
Reasoning · Vision · Tools
TextImageVideoPDFInput$2/M
TextOutput$6/M

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

PaidProprietary961/1040
Qwen

Qwen3.7 Flash

CTX1M
67Quality
Reasoning · Vision · Tools
TextImageVideoInput$0.03/M
TextOutput$0.13/M

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

PaidProprietary950/1040
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot