deepseek-r1-distill-qwen-32b

Name: deepseek-r1-distill-qwen-32b
Author: NVIDIA

reasoning32B

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Model IDdeepseek-ai/deepseek-r1-distill-qwen-32b

ProviderNVIDIA

License—

Parameters32B

Status—

Input modalitiestext

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date—

Deprecation date—

Typereasoning

Reasoning tokens—

Max input—

Open weight—

Sourceofficial

Last updated2026-03-23

Model	Caps	Perf	Speed	Context	Max out
deepseek-r1-distill-llama-8b	RVTS	—	—	—	—
deepseek-r1-distill-qwen-14b	RVTS	—	—	—	—
deepseek-r1-distill-qwen-32b	RVTS	—	—	—	—
deepseek-r1-distill-qwen-7b	RVTS	—	—	—	—

GET/v1/models/nvidia/deepseek-ai/deepseek-r1-distill-qwen-32b

deepseek-ai/deepseek-r1-distill-qwen-32b

Changes · 3 entries

deepseek-ai/deepseek-r1-distill-qwen-32bupdateb301ebeMar 23, 2026, 11:47 PM

modalitiesinput["text"]output["text"]

deepseek-ai/deepseek-r1-distill-qwen-32bupdate2b100acMar 23, 2026, 05:30 AM

model_typereasoning

parameters32

deepseek-ai/deepseek-r1-distill-qwen-32bcreate7f5c66fMar 21, 2026, 05:16 AM