compact ouvert multimodal MoE requiring merely 3B actif paramètres par token, enabling rapide local vision-langue exécution.
Technical Specifications
- Provider
- Alibaba
- Category
- open-source
- Release Date
- 2026-02
- Batch API Discount
- Standard rate
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- qwen3-5-35b-a3b-instruct
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2028+)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Free across full context window (only KV-cache VRAM scales)
- Prompt Cache Write & TTL Policy
- Automatic prefix KV-caching in vLLM / SGLang (0 cost)
- Computer Use & Browser GUI Agent
- Supported (Screen coordinate grounding, browser & desktop GUI action loops)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 22 GB VRAM (4-bit Quantized) · 75 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Qwen3.5 35B-A3B Cost, Context, Hardware & API Integration
Open-weights or free-tier model: $0 API license cost when self-hosted.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Qwen3.5 35B-A3B:
Benchmark Scores & 6-Axis Capability Radar
- GPQA Diamond
- 59%
- MMLU-Pro
- 76.5%
- HumanEval
- 86%
- Chatbot Arena Elo
- 1305pts
Strengths
- peut run smoothly sur un unique grand public GPU (RTX 3090 / 4090 avec INT4/INT8)
- Impressive multimodal response velocity exceeding 120 tokens/sec
- Solid OCR performances sur quotidien documents et web captures
Limitations & Trade-offs
- complexe mathématique dérivation sur engineering schematics peut be inconsistent
- fenêtre de contexte récupération degrades slightly past 180K tokens
Editorial Assessment
un brilliant léger multimodal marvel bringing practical vision AI à grand public desktops.
Best for: local desktop AI assistants, périphérie vision appliances, et en temps réel screen inspection
Compare Qwen3.5 35B-A3B
Frequently Asked Questions about Qwen3.5 35B-A3B
How much does the Qwen3.5 35B-A3B API cost per 1M tokens?+
Qwen3.5 35B-A3B by Alibaba is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the Qwen3.5 35B-A3B pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Qwen3.5 35B-A3B's context window?+
Qwen3.5 35B-A3B features a 262K tokens context window, which equals approximately 196,608 English words or ~524 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 8,192 tokens.
Can I run Qwen3.5 35B-A3B locally on my own GPU (Open Weights)?+
Yes, Qwen3.5 35B-A3B (35B total (3B active MoE)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Alibaba train on data sent to the Qwen3.5 35B-A3B API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Permissive Open-Weights (Apache 2.0 / MIT Commercial). Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Qwen3.5 35B-A3B perform on coding and reasoning benchmarks?+
Qwen3.5 35B-A3B achieves a composite Intelligence Index of 77/100, scoring N/A% on SWE-bench Verified, 59% on GPQA Diamond, 76.5% on MMLU-Pro, and 1305 pts on Chatbot Arena Elo.
What is Qwen3.5 35B-A3B best used for?+
Qwen3.5 35B-A3B is best suited for: local desktop AI assistants, périphérie vision appliances, et en temps réel screen inspection. Assessment: un brilliant léger multimodal marvel bringing practical vision AI à grand public desktops.
Alibaba Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Alibaba's flagship reasoning tier:
Qwen3.8 Max Preview
Qwen3.7 Plus
Qwen3.7 Max
Qwen3.6 Max Preview
Qwen3.6 Plus
Qwen3.6 Flash
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Qwen3.5 35B-A3B:
L'unité textuelle de base traitée par un modèle linguistique, représentant généralement 3 à 4 caractères ou environ 0,75 mot. Par exemple, une phrase courante est découpée en plusieurs jetons.
Une suite de tests standardisés permettant d'évaluer et de comparer objectivement les performances des modèles d'IA sur des tâches ciblées (code avec SWE-bench, mathématiques avec AIME, etc.).
Le nombre maximal de jetons qu'un modèle peut traiter simultanément (entrée et sortie comprises). Une fenêtre de 1 000 000 jetons permet d'analyser environ 750 000 mots en une seule requête.
La capacité d'un LLM à déterminer quand une action externe est requise et à générer des arguments structurés pour invoquer des API, calculatrices ou bases de données avant de poursuivre.
Un standard ouvert créé par Anthropic permettant aux agents d'IA de se connecter de façon uniforme aux systèmes de fichiers locaux, aux environnements de développement et aux API tierces.
Un réseau neuronal multimodal conçu pour analyser, raisonner et générer conjointement des données visuelles (images, schémas, interfaces) et du langage naturel au sein d'une même structure.
Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.
Sources: Qwen 3.5 Model Family Hub↗