Skip to content

Model Library

AlibabaReleased March 2, 2026

Qwen3.5 4B

Alibaba · Released March 2, 2026

View public research Browse the library

Intelligence score

16

At a glance

Intelligence
16
Speed
32.1tokens/sec
Latency
940mstime to first token
Input price
$0.03per 1M tokens
Output price
$0.15per 1M tokens
Context window
260Ktokens
Parameters
4.66billions

Summary

Comparison summary

Qwen3.5 4B (Non-reasoning) scores 16 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 6). Qwen3.5 4B (Non-reasoning) generates output at 32.1 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Qwen3.5 4B (Non-reasoning) costs $0.03 per 1M input tokens (very competitive, median: $0.15) and $0.15 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.

Specifications

Technical specifications

Model nameQwen3.5 4B
ProviderAlibaba
Release dateMarch 2, 2026
Intelligence score16
Speed32.1 tokens/sec
Latency (TTFT)0.94s
Input price$0.03 / 1M tokens
Output price$0.15 / 1M tokens
Context window260,000 tokens
Parameters4.66B
ReasoningNo
Input modalitiestext, image, video
Output modalities—
Open weightsYes
LicenseApache 2
API availability—
SourceModel Intelligence legacy profile: qwen3-5-4b-non-reasoning

Pricing

Token prices

Price per 1M tokens

Qwen3.5 4B, as listed in the catalog record

Input $0.03 and output $0.15 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$0.03
  2. Output$0.15

Model Intelligence legacy profile: qwen3-5-4b-non-reasoning

FAQ · 19

Frequently asked questions

Qwen3.5 4B (Non-reasoning) was released on March 2, 2026.

Qwen3.5 4B (Non-reasoning) was created by Alibaba.

Qwen3.5 4B (Non-reasoning) scores 16 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 6).

Qwen3.5 4B (Non-reasoning) generates output at 32.1 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).

Qwen3.5 4B (Non-reasoning) has a time to first token (TTFT) of 0.94s (based on the median across providers serving the model), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.54s).

Qwen3.5 4B (Non-reasoning) costs $0.03 per 1M input tokens (very competitive, median: $0.15) and $0.15 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.

Qwen3.5 4B (Non-reasoning) costs $0.03 per 1M input tokens and $0.15 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.04 per 1M tokens. Pricing may vary by provider.

No, Qwen3.5 4B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Qwen3.5 4B (Non-reasoning) supports text, image, and video input.

Qwen3.5 4B (Non-reasoning) supports text output.

Yes, Qwen3.5 4B (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.

Yes, Qwen3.5 4B (Non-reasoning) is multimodal. It can process text, image, and video input and generate text output.

Qwen3.5 4B (Non-reasoning) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Qwen3.5 4B (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Qwen3.5 4B (Non-reasoning) has 4.66 billion parameters.

Qwen3.5 4B (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.

Qwen3.5 4B (Non-reasoning) achieves a score of 16 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Qwen3.5 4B (Non-reasoning) is available via API through 1 provider.

Qwen3.5 4B (Non-reasoning) is available through 1 API provider.