Back to Models
qwen logo
qwen/qwen3-32b
Not Available

Qwen3 32B

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

4/28/2025
40,960 tokens
#146 Text (Math)

Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
include_reasoning
max_tokens
min_p
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p

Max Output Tokens

40,960

Frequently asked questions

Is Qwen3 32B available on FastMetal?
Not at the moment. Qwen3.8 Max (0902), from the same lab, is available on the FastMetal API today.
What is the context window of Qwen3 32B?
40,960 tokens, shared between the prompt and the response.
How does Qwen3 32B rank?
#207 on the public arena's Overall board (ELO 1,347). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,347
#207
ChineseELO: 1,361
#209
EnglishELO: 1,365
#209
germanELO: 1,334
#169
russianELO: 1,327
#215
CodingELO: 1,407
#191
MathELO: 1,399
#146
Creative WritingELO: 1,304
#215
Instruction FollowingELO: 1,331
#209
Hard PromptsELO: 1,367
#202
Multi-TurnELO: 1,338
#212