Qwen3.6 35B A3B model profile
Evidence snapshot:
Qwen3.6 35B A3B is a Alibaba Qwen model profile with a 262,144-token context window. The dated catalog snapshot records text, image, video modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.
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 DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.
Qwen3.6 35B A3B is a reference profile: Alibaba Qwen publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Qwen3.6 35B A3B is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.
Qwen3.6 35B A3B accepts text, image, and video and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, tool calling, video input, and vision as capabilities or interfaces.
The dated reference snapshot lists $0.05 input and $0.7 output per million tokens. Cached input is $0.05 per million tokens.
The 2026-09-06 snapshot includes 1 Artificial Analysis index and AutoExacto results for 11 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
Qwen3.6 35B A3B ranked #98 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.
Profile facts
- Profile type
- Model research profile
- Provider or publisher
- Alibaba Qwen
- Context window
- 262,144 tokens
- Snapshot date
- 2026-09-06
- Knowledge cutoff
- Not disclosed
- Reference catalog ID
- qwen/qwen3.6-35b-a3b
When to pick Qwen3.6 35B A3B
Qwen3.6 35B A3B is a reference profile: Alibaba Qwen publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.
- Reach for it when the input includes images. The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described.
- Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
- Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
Context, modalities, and identity
Qwen3.6 35B A3B accepts text, image, and video and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, tool calling, video input, and vision as capabilities or interfaces.
- Provider or publisher
- Alibaba Qwen
- Context window
- 262,144 tokens
- Maximum output
- 235,929 tokens
- Input modalities
- text, image, and video
- Output modalities
- text
- Knowledge cutoff
- Not disclosed
Model overview
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 DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.
- Reference model ID
- qwen/qwen3.6-35b-a3b
- Canonical version
- qwen/qwen3.6-35b-a3b-20260415
- Hugging Face ID
- Qwen/Qwen3.6-35B-A3B
Capabilities and supported controls
Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.
- 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
- prompt caching
- reasoning controls
- structured output
- text generation
- tool calling
- video input
- vision
Dated pricing snapshot
The dated reference snapshot lists $0.05 input and $0.7 output per million tokens. Cached input is $0.05 per million tokens.
These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.
- Price date
- 2026-09-06
- Input
- $0.05 per 1M tokens
- Cached input
- $0.05 per 1M tokens
- Output
- $0.7 per 1M tokens
Provider routes, performance, and uptime
The snapshot retains 10 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.
- Active provider endpoints
- 10
- Best p50 latency
- 0.47 s
- Best p50 throughput
- 138 tok/s
- Availability with routing
- 99.91% over the sampled window
- Availability without routing
- 98.40% over the sampled window
- Performance date
- 2026-09-06
| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
|---|---|---|---|---|---|---|---|---|
| Darkbloom | fp4 | $0.05 / 1M | $0.7 / 1M | No verified rate | 262,144 tokens | 3.92 s | 53 tok/s | 99.99% |
| AkashML | fp8 | $0.1 / 1M | $0.9 / 1M | $0.05 / 1M | 262,144 tokens | 0.63 s | 56 tok/s | 99.96% |
| DeepInfra | fp8 | $0.1 / 1M | $0.95 / 1M | No verified rate | 262,144 tokens | 1.10 s | 99 tok/s | 98.51% |
| Venice | fp8 | $0.1 / 1M | $1 / 1M | No verified rate | 256,000 tokens | 0.63 s | 52 tok/s | 99.98% |
| Parasail | fp8 | $0.15 / 1M | $1 / 1M | $0.05 / 1M | 262,144 tokens | 0.48 s | 48 tok/s | 99.96% |
| AtlasCloud | fp8 | $0.186 / 1M | $1.11375 / 1M | $0.186 / 1M | 262,144 tokens | 0.97 s | 138 tok/s | 99.96% |
| io.net | fp8 | $0.19 / 1M | $1.19 / 1M | $0.09 / 1M | 262,144 tokens | 0.66 s | 37 tok/s | 99.97% |
| Phala | unknown | $0.2 / 1M | $1.27 / 1M | No verified rate | 262,144 tokens | 2.60 s | 92 tok/s | 99.93% |
| SiliconFlow | fp8 | $0.2 / 1M | $1.6 / 1M | No verified rate | 262,144 tokens | 2.66 s | 69 tok/s | 98.56% |
| CoreWeave | fp8 | $0.25 / 1M | $1.25 / 1M | $0.25 / 1M | 262,144 tokens | 0.47 s | 125 tok/s | 99.95% |
Benchmark evidence and limitations
The 2026-09-06 snapshot includes 1 Artificial Analysis index and AutoExacto results for 11 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
- Coding Index
- 41.9
- AutoExacto coverage
- 11 provider observations over 32 days
AutoExacto provider benchmarks
Rolling provider observations from the cited third-party benchmark view. The lookback is 32 days; GPQA Diamond and TAU-Bench Airline measure different abilities and should not be blended into one score.
| Provider | GPQA Diamond | TAU-Bench Airline | Runs |
|---|---|---|---|
| AkashML | 81.26% | 75.51% | 5 |
| AtlasCloud | 85% | 57.96% | 5 |
| auto-routing | 76.65% | 66.96% | 5 |
| CoreWeave | 83.93% | — | 5 |
| Darkbloom | 44.55% | 75.2% | 5 |
| DeepInfra | 60.76% | 75.47% | 5 |
| io.net | 70.36% | 42.07% | 5 |
| Parasail | 84.61% | 75.98% | 5 |
| Phala | 82.95% | 73.3% | 5 |
| SiliconFlow | 82.94% | — | 5 |
| Venice | 80.84% | 35.1% | 5 |
Popularity and market context
Qwen3.6 35B A3B ranked #98 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
- Third-party catalog rank
- #98
- Global market share
- Not inferred
- Observation date
- 2026-09-06
Frequently asked questions
When should I use Qwen3.6 35B A3B?
Qwen3.6 35B A3B is a reference profile: Alibaba Qwen publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when the input includes images: The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
What is Qwen3.6 35B A3B?
Qwen3.6 35B A3B is a Alibaba Qwen model profile with a 262,144-token context window. The dated catalog snapshot records text, image, video modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.
What context window does Qwen3.6 35B A3B have?
The dated profile lists 262,144 tokens of context and up to 235,929 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.
What benchmark evidence is available for Qwen3.6 35B A3B?
The 2026-09-06 snapshot includes 1 Artificial Analysis index and AutoExacto results for 11 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Is Qwen3.6 35B A3B available through Kendr?
This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.
Does the popularity rank represent Qwen3.6 35B A3B's global market share?
Qwen3.6 35B A3B ranked #98 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. No global market-share percentage is inferred when the source does not publish one.
Sources and evidence dates
- Qwen3.6 35B A3B third-party catalog record (catalog, checked 2026-09-06)
- Third-party model catalog methodology (methodology, checked 2026-09-06)
- Alibaba Qwen official model documentation (primary, checked 2026-09-06)
- Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
- Qwen3.6 35B A3B third-party catalog record (benchmark, checked 2026-09-06)