Qwen

Qwen3.6 35B-A3B

CTX262K

66Quality

Reasoning · Vision · Tools

Input$0.25/M

Output$1.49/M

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Open weightsApache 2.0875/1044

Drag to turn

QwenTextCommon

Qwen3.6 35B-A3B

Open multimodal Qwen MoE for local agents that need vision, audio, and code

qwen3.6-35b-a3b

Type: Text
Quality: 66 · Top 34% on the Epoch Capabilities Index
Context window: 262,144 tokens
Max output: 65,536 tokens
Input price: $0.25 / 1M tokens
Output price: $1.49 / 1M tokens
Cache read: —
Cache write: —
Parameters: 36B (35,951,822,704)
Downloads: 3.7M in the last 30 days
Likes: 3K
Access to weights: Open download
Released: Apr 17, 2026
Knowledge cutoff: —
Takes in: Text, Image, Audio, Video
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Open weights
License: Apache 2.0
Rarity: Common
Set number: 875/1044

Open Qwen docs Weights on Hugging Face Quality 66 Where to run it 36 Evolution 7/8 Race it 116 tok/s Meet its creature Battle Gemini 3.1 Flash Lite

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: www.alibabacloud.com.

How good is it?

Public leaderboard scores for Qwen3.6 35B-A3B, refreshed daily from Epoch AI and LMArena.

Top 34% of the 277 models on the Epoch Capabilities Index: #95.

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#95 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.144.1 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

33 providers sell Qwen3.6 35B-A3B through an API, and 3 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

Cheapestengy$0.045 in · $0.30 out
Free to try3 providersNaN, QVAC, Umans AI Coding Plan
From the labAlibaba$0.25 in · $1.49 out
Fastest on Hugging FaceDeepInfra116 tokens/s

API providers

Provider	Input	Output	Context
NaNFree`qwen3.6`	Free	Free	262K
QVACFree`qwen3.6-35b-a3b`	Free	Free	262K
Umans AI Coding PlanFree`umans-qwen3.6-35b-a3b`	Free	Free	262K
engyCheapest paid`qwen3.6-35b-a3b`	$0.045	$0.30	208K
Boundless`qwen3.6`	$0.04	$0.35	262K
EmpirioLabs AI`qwen3-6-35b-a3b`	$0.07	$0.42	131K
Zenifra`alibaba/qwen3.6-35b-a3b`	$0.19	$0.48	262K
AKI.IO`qwen3.6-35b`	$0.15	$0.50	256K
Cortecs`qwen3.6-35b-a3b`	$0.17	$0.56	262K
SaladCloud AI Gateway`qwen3.6-35b-a3b`	$0.09	$0.60	262K

Show 23 more providers

Provider	Input	Output	Context
NanoGPT`qwen/qwen3.6-35b-a3b`	$0.11	$0.80	262K
Deep Infra`Qwen/Qwen3.6-35B-A3B`	$0.10	$0.95	262K
Venice AI`qwen3-6-35b-a3b`	$0.10	$1.00	256K
Pioneer`Qwen/Qwen3.6-35B-A3B`	$0.14	$1.00	262K
Ambient`qwen/qwen3.6-35b-a3b`	$0.15	$1.00	262K
Kilo Gateway`qwen/qwen3.6-35b-a3b`	$0.15	$1.00	262K
OpenRouter`qwen/qwen3.6-35b-a3b`	$0.15	$1.00	262K
CoreWeave`Qwen/Qwen3.6-35B-A3B`	$0.25	$1.25	262K
evroc`Qwen/Qwen3.6-35B-A3B`	$0.34	$1.38	262K
AlibabaOfficial`qwen3.6-35b-a3b`	$0.25	$1.49	262K
DevPass (LLM Gateway)`qwen3.6-35b-a3b`	$0.25	$1.49	262K
LLM Gateway`novita/qwen3.6-35b-a3b`	$0.25	$1.49	262K
Merge Gateway`qwen/qwen3.6-35b-a3b`	$0.25	$1.49	262K
Novita AI`qwen/qwen3.6-35b-a3b`	$0.25	$1.49	262K
Opper`qwen3.6-35b-a3b`	$0.25	$1.49	262K
OrcaRouter`qwen/qwen3.6-35b-a3b`	$0.25	$1.49	262K
Scaleway`qwen3.6-35b-a3b`	$0.25	$1.50	128K
AIHubMix`qwen3.6-35b-a3b`	$0.25	$1.52	262K
SiliconFlow`Qwen/Qwen3.6-35B-A3B`	$0.20	$1.60	262K
302.AI`qwen3.6-35b-a3b`	$0.28	$1.71	262K
SiliconFlow (China)`Qwen/Qwen3.6-35B-A3B`	$0.23	$1.86	262K
GreenPT`qwen3.6-35b-a3b`	$0.34	$2.05	262K
LLMTR`qwen3-6-35b`	$5.00	$10.00	16K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraFastestTools	$0.10	$0.95	262K	116 tok/s	0.5s
ScalewayTools	$0.28	$1.71	—	68 tok/s	0.4s
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.

Face off

Current text models from other labs at a similar output price.

Qwen3.6 35B-A3B

Qwen3.6 35B-A3B

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Hugging Face Inference Providers

Face off

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