Qwen3.5 9B vs Qwen3.5 35B-A3B
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Qwen3.5 9B dari Alibaba dan Qwen3.5 35B-A3B dari Alibaba adalah dua model AI unggulan. Qwen3.5 9B menawarkan jendela konteks 262.1K token dengan harga $0.00/$0.00 per 1 juta token, sedangkan Qwen3.5 35B-A3B menyediakan konteks 262.1K token seharga $0.00/$0.00 per 1 juta token. Berikut perbandingan lengkap benchmark, latensi, dan biayanya.
Ganti & Bandingkan Model Apa Saja
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Qwen3.5 9B
Model Dasar Bobot TerbukaQwen3.5 9B dari Alibaba adalah model AI yang dirancang untuk self-hosting di server pribadi, fine-tuning, dan kedaulatan data penuh, menghadirkan jendela konteks 262K, kecepatan 165 token/detik, indeks kecerdasan 70/100, serta akses gratis
$0.00 / 1M
$0.00 / 1M
262.1K tokens
N/A
Qwen3.5 35B-A3B
AI Multimodal AsliQwen3.5 35B-A3B dari Alibaba adalah model AI yang dirancang untuk pemahaman multimodal asli (teks & visual) serta analisis dokumen kompleks, menghadirkan jendela konteks 262K, kecepatan 125 token/detik, indeks kecerdasan 77/100, serta akses
$0.00 / 1M
$0.00 / 1M
262.1K tokens
N/A
Perbedaan Utama Sekilas
- Both models cost the same under this workload — choose on capability, not price.
- Qwen3.5 9B is faster at 165 tok/s vs 125 tok/s.
| Feature | Qwen3.5 9B | Qwen3.5 35B-A3B |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 70 | 77 |
Provider | Alibaba | Alibaba |
Input Price Cost per million input tokens | $0.00 / 1M | $0.00 / 1M |
Output Price Cost per million output tokens | $0.00 / 1M | $0.00 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $0.00 / 1M | $0.00 / 1M |
Context Window Maximum input + output tokens | 262.1K tokens~393 A4 pages of text | 262.1K tokens~393 A4 pages of text |
Max Output Tokens Per single request | 8K | 8K |
Throughput Speed Tokens generated per second | 165 tok/s | 125 tok/s |
SWE-bench Verified Real-world software engineering | N/A | N/A |
GPQA Diamond Graduate-level reasoning | N/A | 59% |
Siapa Unggul di Mana?
At-a-glance decision frameworkEvaluations ongoing
Skor Benchmark Terverifikasi
Official evaluation metrics verified by independent third-party research labs.
Challenging questions created by domain experts to test complex PhD-level reasoning.
Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.
Crowdsourced human preference evaluation based on blind, head-to-head model battles.
Tokens emitted per second during active generation streaming.
Latensi & Waktu Respons
Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.
Simulator Biaya Token Interaktif
Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.
Qwen3.5 9B · Strengths & Key Advantages
- Jendela konteks 262K dengan kapasitas output maksimum hingga 8K token (MMLU-Pro 68% · Arena Elo 1230)
- Kecepatan generasi tinggi 165 token/detik dengan latensi token pertama (TTFT) hanya 220 ms
- Bobot terbuka (9B) yang siap di-hosting mandiri di GPU lokal atau cloud privat melalui vLLM dan Ollama
Considerations & Trade-offs
- Membutuhkan infrastruktur GPU dengan kapasitas VRAM yang memadai untuk eksekusi lokal presisi penuh
- Pada tugas pembuktian ilmiah tingkat ekstrem, model penalaran berat kelas atas memberikan kedalaman lebih tinggi
Qwen3.5 35B-A3B · Strengths & Key Advantages
- Jendela konteks 262K dengan kapasitas output maksimum hingga 8K token (GPQA Diamond 59% · MMLU-Pro 76.5%)
- Kecepatan generasi tinggi 125 token/detik dengan latensi token pertama (TTFT) hanya 340 ms
- Bobot terbuka (35B total (3B MoE)) yang siap di-hosting mandiri di GPU lokal atau cloud privat melalui vLLM dan Ollama
Considerations & Trade-offs
- Membutuhkan infrastruktur GPU dengan kapasitas VRAM yang memadai untuk eksekusi lokal presisi penuh
- Pada tugas pembuktian ilmiah tingkat ekstrem, model penalaran berat kelas atas memberikan kedalaman lebih tinggi
Token Use & Task Economics
Estimated cost and token consumption to complete one representative agentic task.
| Metric | Qwen3.5 9B | Qwen3.5 35B-A3B |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.00 | $0.00 |
Output Tokens / Task Tokens generated per task | 10K | 14K |
Reasoning Tokens / Task Thinking tokens burned per task | 0K | 0K |
Spesifikasi Teknis
Architecture, release timeline, capabilities, and modalities.
| Feature | Qwen3.5 9B | Qwen3.5 35B-A3B |
|---|---|---|
| Official API Model ID (SDK) | qwen3-5-9b-instruct | qwen3-5-35b-a3b-instruct |
| API Protocol | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI |
| Release Date | 2026-02 | 2026-02 |
| Knowledge Cutoff | December 2025 | December 2025 |
| Architecture | Compact Dense Autoregressive Transformer | Lightweight Multimodal MoE Transformer |
| Parameters | 9B | 35B total (3B active MoE) |
| Enterprise Rate Limits (RPM / TPM) | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud |
| Long-Context Tier (>128K/200K) | Free across full context window (only KV-cache VRAM scales) | Free across full context window (only KV-cache VRAM scales) |
| Prompt Cache Policy & TTL | Automatic prefix KV-caching in vLLM / SGLang (0 cost) | Automatic prefix KV-caching in vLLM / SGLang (0 cost) |
| Computer Use / GUI Agent | API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop) | 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 | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema |
| Web Search Grounding & Sandbox | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools |
| Official Fine-Tuning Support | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) |
| Multimodal Token Billing | Text BPE (~4 chars/token) | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) |
| Quantization & Min GPU VRAM | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 6 GB VRAM (4-bit Quantized) · 19 GB VRAM (Native BF16) | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 22 GB VRAM (4-bit Quantized) · 75 GB VRAM (Native BF16) |
| Safety & Frontier Classification | Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma) | Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma) |
| Enterprise Compliance (ZDR/HIPAA/SOC2) | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control |
| Input Modalities | text | text, vision |
| Output Modalities | text | text |
Qwen3.5 9B vs Qwen3.5 35B-A3B: Jawaban Cepat (FAQ)
Which is more intelligent, Qwen3.5 9B or Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is more intelligent. It scores 77 compared with 70 on the composite Intelligence Index.
Which model is faster?
Qwen3.5 9B is faster, generating 165 tokens per second compared with 125 tokens per second.
Which model has lower latency?
Qwen3.5 9B has lower latency, with a time to first token of 0.22s compared with 0.34s.
Kesimpulan
Baik Qwen3.5 9B (Sangat cocok untuk self-hosting di server pribadi, fine-tuning, dan kedaulatan data penuh, sistem RAG perusahaan, dan integrasi API skala produksi.) maupun Qwen3.5 35B-A3B (Sangat cocok untuk pemahaman multimodal asli (teks & visual) serta analisis dokumen kompleks, sistem RAG perusahaan, dan integrasi API skala produksi.) sangat tangguh: Qwen3.5 35B-A3B unggul dalam penalaran dan pemrograman, Qwen3.5 9B memberikan kecepatan generasi token lebih tinggi, dan Qwen3.5 9B lebih hemat biaya untuk penggunaan API skala besar.
Pertanyaan Umum (FAQ)
Mana yang lebih baik untuk coding dan penalaran, Qwen3.5 9B atau Qwen3.5 35B-A3B?+
Dalam indeks kecerdasan gabungan dan benchmark coding, Qwen3.5 35B-A3B memimpin. Lihat skor SWE-bench dan GPQA di atas untuk detailnya.
Berapa perbandingan harga API Qwen3.5 9B vs Qwen3.5 35B-A3B?+
Qwen3.5 9B mengenakan biaya $0.00 / $0.00 per 1M token input/output, sedangkan Qwen3.5 35B-A3B sebesar $0.00 / $0.00. Secara keseluruhan, Qwen3.5 9B lebih hemat biaya.
Model mana yang memiliki jendela konteks lebih besar dan kecepatan lebih tinggi?+
Qwen3.5 9B mendukung konteks 262.1K token dibandingkan 262.1K token pada Qwen3.5 35B-A3B, sementara Qwen3.5 9B unggul dalam kecepatan output token per detik.
Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.
Related reading
- DeepSeek Chat vs Qwen3.5 9B: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Qwen3.5 35B-A3B vs DeepSeek Chat: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Qwen3.5 35B-A3B vs Qwen3.5 27B: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Aion-3.0 vs Aion-Mini: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Aion-3.0 vs Gemini 3.6 Flash: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Aion-Mini vs Laguna XS 2.1: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
Sumber resmi: Dokumentasi API resmi Alibaba & Alibaba serta evaluasi benchmark independen (2026).