Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · nvidia

OpenCodeReasoning-Nemotron-1.1-32B

OpenCodeReasoning-Nemotron-1.1-32B is a 32.76B-parameter Qwen2 code-reasoning model from nvidia. According to the model card, it derives from Qwen2.5-32B-Instruct with 64K-token context.

Publisher
nvidia
Task
text-generation
Model type
qwen2
License
Unknown
Library
transformers
Publication status
Accepted · not indexed

Model overview

OpenCodeReasoning-Nemotron-1.1-32B is published by nvidia as a Qwen2 text-generation model. The captured configuration identifies Qwen2ForCausalLM and Safetensors metadata reports 32,763,876,352 parameters. According to the model card, it derives from Qwen2.5-32B-Instruct for code reasoning with 64K-token context.

Recorded capabilities

Code-reasoning post-training

According to the model card, the model is a dense decoder-only derivative of Qwen2.5-32B-Instruct post-trained for reasoning for code generation.

64K-token context

According to the model card, the model supports 64K-token context, specified as up to 65,536 tokens.

Reported LiveCodeBench score

According to the model card, the publisher reports 69.9 Pass@1 on LiveCodeBench v5, above the listed 32B distilled peers.

Use cases in the source record

  • Competitive-coding generation workflows that use step-by-step reasoning before responding, following the card's inference pattern.
  • Code-reasoning distillation research referencing the documented OpenCodeReasoning dataset and LiveCodeBench evaluation setup.

Limitations and unknowns

  • According to the model card, benchmark figures are publisher-reported averages; no independent Ethen evaluation was extracted.
  • According to the model card, governing terms require review of the NVIDIA Open Model License Agreement before use.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • No standalone Hub license value was extracted from this record.

Source and provenance

Source: nvidia/OpenCodeReasoning-Nemotron-1.1-32B

Captured: Unknown. Processed: 2026-09-07T19:35:59.411698+00:00.

OpenCodeReasoning-Nemotron-1.1-32B Overview Description: OpenCodeReasoning-Nemotron-1.1-32B is a large language model (LLM) which is a derivative of Qwen2.5-32B-Instruct (AKA the reference model). It is a reasoning model that is post-trained for reasoning for code generation. The model supports a context length of 64k tokens. This model is ready for commercial/non-commercial use. Results Below results are the average of 64 evaluations on LiveCodeBench (v5) [2408-2501]. Model Pass@1 DeepSeek-R1-0528 73.4 DeepSeek-R1 65.6 QwQ-32B 61.3 Distilled 7B+ Models Bespoke-Stratos-7B 14.7 OpenThinker-7B 25.5 R1-Distill-Qwen-7B 38.0 OlympicCoder…

F001F002F003F004F005F006F008F009F010F012F013F015F017F018F019F020F022