Qwen

Qwen3.5-9B

SIZE9.7B

55Quality

Vision

Downloads7.5M/mo

Likes2.2K

Vision-language model from Qwen, 9.7B parameters.

Open weightsApache 2.0806/1044

Drag to turn

QwenTextPromo

Qwen3.5-9B

Vision-language model from Qwen, 9.7B parameters.

Qwen/Qwen3.5-9B

Type: Text
Quality: 55 · Top 45% on the Epoch Capabilities Index
Parameters: 9.7B (9,653,104,368)
Downloads: 7.5M in the last 30 days
Likes: 2.2K
Access to weights: Open download
On Hugging Face since: Feb 27, 2026
Takes in: Text, Image
Puts out: Text
Access: Open weights
License: Apache 2.0
Rarity: Promo
Set number: 806/1044

Open on Hugging Face Quality 55 Where to run it 26 Evolution 6/8 Race it 114 tok/s Meet its creature Battle GLM-5.3-Flash

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 Qwen3.5-9B, refreshed daily from Epoch AI and LMArena.

Top 45% of the 277 models on the Epoch Capabilities Index: #124.

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

Epoch Capabilities Index#124 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.139.4 index

Benchmarks Epoch AI runs

Scores from Epoch AI, 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

22 providers sell Qwen3.5-9B through an API, and 4 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestEmpirioLabs AI$0.09 in · $0.13 out
Free to try2 providersAtomic Chat, QVAC
Fastest on Hugging FaceTogether AI114 tokens/s

API providers

Provider	Input	Output	Context
Atomic ChatFree`Qwen3_5-9B-Q4_K_M`	Free	Free	33K
QVACFree`qwen3.5-9b`	Free	Free	33K
EmpirioLabs AICheapest paid`qwen3-5-9b`	$0.09	$0.13	262K
Merge Gateway`qwen/qwen3.5-9b`	$0.09	$0.13	262K
CrofAI`qwen3.5-9b`	$0.04	$0.15	262K
NanoGPT`qwen/qwen3.5-9b`	$0.05	$0.15	262K
Deep Infra`Qwen/Qwen3.5-9B`	$0.10	$0.15	262K
DevPass (LLM Gateway)`qwen3.5-9b`	$0.10	$0.15	262K
Kilo Gateway`qwen/qwen3.5-9b`	$0.10	$0.15	256K
LLM Gateway`deepinfra/qwen3.5-9b`	$0.10	$0.15	262K

Show 12 more providers

Provider	Input	Output	Context
OpenRouter`qwen/qwen3.5-9b`	$0.10	$0.15	262K
SiliconFlow`Qwen/Qwen3.5-9B`	$0.10	$0.15	262K
Venice AI`qwen3-5-9b`	$0.10	$0.15	256K
Cortecs`qwen3.5-9b`	$0.11	$0.17	262K
OVHcloud AI Endpoints`qwen3.5-9b`	$0.12	$0.18	262K
TensorX`qwen/qwen3.5-9b`	$0.15	$0.20	262K
Together AI`Qwen/Qwen3.5-9B`	$0.17	$0.25	262K
Pioneer`Qwen/Qwen3.5-9B`	$0.30	$0.30	33K
Mixlayer`qwen/qwen3.5-9b`	$0.10	$0.40	262K
routing.run`qwen3.5-9b`	$0.16	$0.48	262K
Regolo AI`qwen3.5-9b`	$0.15	$0.60	262K
SiliconFlow (China)`Qwen/Qwen3.5-9B`	$0.22	$1.74	262K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraTools	$0.10	$0.15	262K	94 tok/s	0.5s
OVHcloudTools	$0.12	$0.18	262K	38 tok/s	0.4s
Together AIFastestTools	$0.17	$0.25	262K	114 tok/s	0.3s
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.

Qwen3.5-9B

Qwen3.5-9B

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Hugging Face Inference Providers

More from Qwen

Qwen-Image-2.1-Turbo

Qwen3.8 Omni Flash

Qwen-Image-2.1

Qwen3.8 Flash

Qwen3.8-Flash-Next

Qwen3.8-2.4T-A95B

Qwen3.8-27B

Qwen3.8 Max