Skip to content
AI Atlas
ModelActive

Qwen3.6 35B A3B

Qwenhuggingface.co/Qwen/Qwen3.6-35B-A3B

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

Open in Graph
data quality68

Updated 5 h ago · first seen 11 Sept 2026

model_01M294WW00HFKTBSY2DM4THGPV

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 7 h agomedium

Model card

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Active parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Capabilities

Modalities

Modalities
imagetextvideo
Input
imagetextvideo
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Yes

    OpenRouter public model & pricing listing · T2

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.
Current prices per 1M tokens
ProviderInput / 1MOutput / 1MCached inBatch in / outContextObservedSource
OpenRouterqwen/qwen3.6-35b-a3b$0.10$0.90$0.05262.1K4 h agoopenrouter.aiT2

USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 1 provider

Output price history of Qwen3.6 35B A3B$0$0.20$0.40$0.60$0.80$1$1.2Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.90 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.9011 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of Qwen3.6 35B A3B$0$0.02$0.04$0.06$0.08$0.10$0.12Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.10 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.1011 Sept 2026

Hardware fit37

Estimated

36 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit21.2 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit21.2 GB est.Yes
Apple M2 Ultra4bit21.2 GB est.Yes
Apple M1 Ultra4bit21.2 GB est.Yes
Apple M3 Max4bit21.2 GB est.Yes
Apple M4 Max4bit21.2 GB est.Yes
Mac Studio (Apple M5 Max)4bit21.2 GB est.Yes
MacBook Pro (Apple M5 Max)4bit21.2 GB est.Yes
Apple M2 Max4bit21.2 GB est.Yes
Apple M1 Max4bit21.2 GB est.Yes
Apple M4 Pro4bit21.2 GB est.Yes
Mac mini (Apple M5 Pro)4bit21.2 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit21.2 GB est.Yes
Apple M3 Pro4bit21.2 GB est.Yes
Apple M1 Pro4bit21.2 GB est.Yes
Apple M2 Pro4bit21.2 GB est.Yes
Apple M44bit21.2 GB est.Yes
iMac (Apple M4)4bit21.2 GB est.Yes
Mac mini (Apple M6)4bit21.2 GB est.Yes
MacBook Air (Apple M5)4bit21.2 GB est.Yes
MacBook Pro (Apple M5)4bit21.2 GB est.Yes
Apple M24bit21.2 GB est.Yes
Apple M34bit21.2 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB21.2 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB21.2 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB21.2 GB est.Yes
NVIDIA A100 80GB4bit80 GB21.2 GB est.Yes
NVIDIA H100 SXM4bit80 GB21.2 GB est.Yes
NVIDIA H100 NVL4bit94 GB21.2 GB est.Yes
NVIDIA DGX Spark4bit128 GB21.2 GB est.Yes
NVIDIA H2004bit141 GB21.2 GB est.Yes
NVIDIA H200 NVL4bit141 GB21.2 GB est.Yes
NVIDIA B2004bit180 GB21.2 GB est.Yes
AMD Instinct MI300X4bit192 GB21.2 GB est.Yes
AMD Instinct MI325X4bit256 GB21.2 GB est.Yes
NVIDIA DGX B2004bit1,440 GB21.2 GB est.Yes
Apple M14bit21.2 GB est.No
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
DESCENDANTS 0 · ARTIFACTS7 quantizationsartifacts · collapsed7 quantizations — artifacts · collapsedQwen3.6 35B A3B36B params · this modelQwen3.6 35B A3B — 36B params · this model

    Change history40

    Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

    Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

    Back to today →

    Attributes as of 12 Sept 2026 42 claims in force

    Release date
    15 Apr 2026
    Openness
    open-weights
    License
    Apache-2.0
    Architecture
    Qwen3_5MoeForConditionalGeneration
    Parameters
    36B
    Active parameters
    3B
    Context window
    262.1K tokens
    Max output
    235.9K tokens
    Modalities
    image, text, video
    Input modalities
    image, text, video
    Output modalities
    text
    Tokenizer
    Qwen
    File size
    71.9 GB
    Hugging Face repo
    Qwen/Qwen3.6-35B-A3B
    Pipeline tag
    image-text-to-text
    Downloads
    3,931,259
    Likes
    2,801
    Aa context window
    262,144
    Aa openness
    open-weights
    Commercial use allowed
    Yes
    Derivatives allowed
    Yes
    Gated
    No
    Hf inference providers
    deepinfra, featherless-ai, scaleway
    Last modified
    2026-04-24T02:53:42+00:00
    Library name
    transformers
    License url
    https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE
    Aa median output tokens per second
    139.2
    Downloads all time
    27,245,155
    Model type
    qwen3_5_moe
    Openrouter id
    qwen/qwen3.6-35b-a3b
    Openrouter listed at
    27 Apr 2026
    Reasoning
    Yes
    Redistribution allowed
    Yes
    Structured output
    Yes
    Supported parameters
    frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
    Tags
    transformers, safetensors, qwen3_5_moe, image-text-to-text
    Tool calling
    Yes
    Vision
    Yes
    Weights available
    Yes
    Weights dtype
    BF16
    40 claims · 35 properties

    Release daterelease_date6

    Claim history for Release date
    ValueValid from → toStatusSourceConfidenceExtractor
    15 Apr 2026currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
    27 Apr 2026supersededOpenRouter public model & pricing listingT2mediumdeterministic
    15 Apr 2026supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
    27 Apr 2026supersededOpenRouter public model & pricing listingT2mediumdeterministic
    15 Apr 2026supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
    27 Apr 2026supersededOpenRouter public model & pricing listingT2mediumdeterministic

    Opennessopenness1

    Claim history for Openness
    ValueValid from → toStatusSourceConfidenceExtractor
    open-weightscurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Licenselicense1

    Claim history for License
    ValueValid from → toStatusSourceConfidenceExtractor
    apache-2.0currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Architecturearchitecture1

    Claim history for Architecture
    ValueValid from → toStatusSourceConfidenceExtractor
    Qwen3_5MoeForConditionalGenerationcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Parametersparameter_count1

    Claim history for Parameters
    ValueValid from → toStatusSourceConfidenceExtractor
    36BcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Active parametersactive_parameter_count1

    Claim history for Active parameters
    ValueValid from → toStatusSourceConfidenceExtractor
    3BcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Context windowcontext_length1

    Claim history for Context window
    ValueValid from → toStatusSourceConfidenceExtractor
    262.1K tokenscurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Max outputmax_output_tokens1

    Claim history for Max output
    ValueValid from → toStatusSourceConfidenceExtractor
    235.9K tokenscurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Modalitiesmodalities1

    Claim history for Modalities
    ValueValid from → toStatusSourceConfidenceExtractor
    image, text, videocurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Input modalitiesmodalities_input1

    Claim history for Input modalities
    ValueValid from → toStatusSourceConfidenceExtractor
    image, text, videocurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Output modalitiesmodalities_output1

    Claim history for Output modalities
    ValueValid from → toStatusSourceConfidenceExtractor
    textcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Tokenizertokenizer1

    Claim history for Tokenizer
    ValueValid from → toStatusSourceConfidenceExtractor
    QwencurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    File sizefile_size_gb1

    Claim history for File size
    ValueValid from → toStatusSourceConfidenceExtractor
    71.9 GBcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Hugging Face repohf_repo1

    Claim history for Hugging Face repo
    ValueValid from → toStatusSourceConfidenceExtractor
    Qwen/Qwen3.6-35B-A3BcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Pipeline tagpipeline_tag1

    Claim history for Pipeline tag
    ValueValid from → toStatusSourceConfidenceExtractor
    image-text-to-textcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Model cardmodel_card_url1

    Claim history for Model card
    ValueValid from → toStatusSourceConfidenceExtractor
    https://huggingface.co/Qwen/Qwen3.6-35B-A3BcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Downloadsmetric.downloads1

    Claim history for Downloads
    ValueValid from → toStatusSourceConfidenceExtractor
    3,931,259currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Likesmetric.likes1

    Claim history for Likes
    ValueValid from → toStatusSourceConfidenceExtractor
    2,801currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Descriptiondescription1

    Claim history for Description
    ValueValid from → toStatusSourceConfidenceExtractor
    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Gatedgated1

    Claim history for Gated
    ValueValid from → toStatusSourceConfidenceExtractor
    NocurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Hf inference providershf_inference_providers1

    Claim history for Hf inference providers
    ValueValid from → toStatusSourceConfidenceExtractor
    deepinfra, featherless-ai, scalewaycurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Last modifiedlast_modified1

    Claim history for Last modified
    ValueValid from → toStatusSourceConfidenceExtractor
    2026-04-24T02:53:42+00:00currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Library namelibrary_name1

    Claim history for Library name
    ValueValid from → toStatusSourceConfidenceExtractor
    transformerscurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    License urllicense_url1

    Claim history for License url
    ValueValid from → toStatusSourceConfidenceExtractor
    https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSEcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1

    Claim history for Aa median output tokens per second
    ValueValid from → toStatusSourceConfidenceExtractor
    128.8currentcurrentArtificial AnalysisT2mediumdeterministic

    Downloads all timemetric.downloads_all_time1

    Claim history for Downloads all time
    ValueValid from → toStatusSourceConfidenceExtractor
    27,245,155currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Model typemodel_type1

    Claim history for Model type
    ValueValid from → toStatusSourceConfidenceExtractor
    qwen3_5_moecurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Openrouter idopenrouter_id1

    Claim history for Openrouter id
    ValueValid from → toStatusSourceConfidenceExtractor
    qwen/qwen3.6-35b-a3bcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Reasoningreasoning1

    Claim history for Reasoning
    ValueValid from → toStatusSourceConfidenceExtractor
    YescurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Structured outputstructured_output1

    Claim history for Structured output
    ValueValid from → toStatusSourceConfidenceExtractor
    YescurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Supported parameterssupported_parameters1

    Claim history for Supported parameters
    ValueValid from → toStatusSourceConfidenceExtractor
    frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_pcurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Tagstags1

    Claim history for Tags
    ValueValid from → toStatusSourceConfidenceExtractor
    transformers, safetensors, qwen3_5_moe, image-text-to-textcurrentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Tool callingtool_calling1

    Claim history for Tool calling
    ValueValid from → toStatusSourceConfidenceExtractor
    YescurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Visionvision1

    Claim history for Vision
    ValueValid from → toStatusSourceConfidenceExtractor
    YescurrentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

    Weights dtypeweights_dtype1

    Claim history for Weights dtype
    ValueValid from → toStatusSourceConfidenceExtractor
    BF16currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

    Provenance

    Attributed facts

    36

    Source tiers

    T236

    Freshest observation

    5 h ago

    Conflicts

    None

    Source documents 12

    Source documents
    SourceDocumentTypeTierLast observedSnapshots
    OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary4 h ago6
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/Qwen/Qwen3.6-35B-A3B/raw/main/README.md model_cardT2· Quality secondary5 h ago1
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/unsloth/Qwen3.6-35B-A3B-MTP-GGUF model_pageT2· Quality secondary6 h ago4
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF model_pageT2· Quality secondary6 h ago4
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/unsloth/Qwen3.6-35B-A3B-NVFP4 model_pageT2· Quality secondary6 h ago4
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/Qwen/Qwen3.6-35B-A3B model_pageT2· Quality secondary6 h ago4
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8 model_pageT2· Quality secondary6 h ago5
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/nvidia/Qwen3.6-35B-A3B-NVFP4 model_pageT2· Quality secondary6 h ago4
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/Intel/Qwen3.6-35B-A3B-int4-mixed-AutoRound model_pageT2· Quality secondary6 h ago4
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/bartowski/Qwen_Qwen3.6-35B-A3B-GGUF model_pageT2· Quality secondary6 h ago5
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=Qwen&p=0&sort=downloads listingT2· Quality secondary6 h ago6
    Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary10 h ago1

    Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

    Data quality (68/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →