Qwen3.5-9B
Qwenhuggingface.co/Qwen/Qwen3.5-9B
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
Updated 5 h ago · first seen 11 Sept 2026
model_01M294WW3ER0NCZXFMCX80TXGW
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
- 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
Benchmarks8
Compare with another model →Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric
No benchmark results recorded
Providers & Pricing3
All offers in the price terminal →USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Price history
Output price · USD / 1M tokens 2 providers
- OpenRouter
- Together AI
- Together AIfirst observed $0.2511 Sept 2026
- OpenRouter$0.15 → $0.2511 Sept 2026
- OpenRouterfirst observed $0.1511 Sept 2026
Input price · USD / 1M tokens 2 providers
- OpenRouter
- Together AI
- Together AIfirst observed $0.1711 Sept 2026
- OpenRouter$0.10 → $0.1711 Sept 2026
- OpenRouterfirst observed $0.1011 Sept 2026
Hardware fit37
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).
Lineage
Open in Graph →- ancestor: Qwen3.5-9B-Base
Timeline14
Full timeline →Qwen3.5-9B scores 14.92% on Humanity's Last Exam
artificial_analysisQwen3.5-9B scores 13.65 on Artificial Analysis Intelligence Index
artificial_analysisTogether AI lists Qwen3.5-9B at $0.17 in / $0.25 out per 1M tokens
together_pricingQwen3.5-9B: release date changed from 2026-02-27 to 2026-03-10
Release date27 Feb 2026→10 Mar 2026openrouterQwen3.5-9B: release date changed from 2026-03-10 to 2026-02-27
Release date10 Mar 2026→27 Feb 2026huggingfaceOpenRouter lists Qwen3.5-9B at $0.17 in / $0.25 out per 1M tokens
openrouterOpenRouter lists Qwen3.5-9B at $0.1 in / $0.15 out per 1M tokens
openrouter
Change history41
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
- 27 Feb 2026
- Openness
- open-weights
- License
- Apache-2.0
- Architecture
- Qwen3_5ForConditionalGeneration
- Parameters
- 9.65B
- Context window
- 262.1K tokens
- Max output
- 235.9K tokens
- Modalities
- image, text, video
- Input modalities
- image, text, video
- Output modalities
- text
- Tokenizer
- Qwen3
- Base model
- Qwen/Qwen3.5-9B-Base
- File size
- 19.3 GB
- Hugging Face repo
- Qwen/Qwen3.5-9B
- Pipeline tag
- image-text-to-text
- Model card
- Downloads
- 10,588,820
- Likes
- 1,924
- Aa context window
- 262,144
- Aa openness
- open-weights
- Commercial use allowed
- Yes
- Derivatives allowed
- Yes
- Gated
- No
- Hf inference providers
- deepinfra, featherless-ai, ovhcloud, together
- Last modified
- 2026-03-02T00:51:43+00:00
- Library name
- transformers
- License url
- https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE
- Aa median output tokens per second
- 91.4
- Downloads all time
- 60,507,487
- Model type
- qwen3_5
- Openrouter id
- qwen/qwen3.5-9b
- Openrouter listed at
- 10 Mar 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, image-text-to-text
- Tool calling
- Yes
- Vision
- Yes
- Weights available
- Yes
- Weights dtype
- BF16, F32
Release daterelease_date6
Opennessopenness1
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Context windowcontext_length1
Max outputmax_output_tokens1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Tokenizertokenizer1
Base modelbase_model1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Model cardmodel_card_url1
Downloadsmetric.downloads1
Likesmetric.likes2
Descriptiondescription1
Gatedgated1
Hf inference providershf_inference_providers1
Last modifiedlast_modified1
Library namelibrary_name1
License urllicense_url1
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1
Downloads all timemetric.downloads_all_time1
Model typemodel_type1
Openrouter idopenrouter_id1
Reasoningreasoning1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Visionvision1
Weights dtypeweights_dtype1
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 8
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 →