OpenReasoning-Nemotron-32B
OpenReasoning-Nemotron-32B is an open-weights language model from NVIDIA, released July 16, 2025. It has 32B parameters (dense).
OpenReasoning-Nemotron-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 about math, code and science solution generation. We evaluated this model with up to 64K output tokens.
Check it against your own PC →
Can you run OpenReasoning-Nemotron-32B locally?
The smallest common GPU it runs on is 16 GB of VRAM (with 32 GB of RAM): Q3_K_M, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 5.2 GB | 11.0 GB | ~3 |
| 8 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 7.2 GB | 9.0 GB | ~3 |
| 12 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 11.2 GB | 5.0 GB | ~5 |
| 16 GB VRAM | Runs, slowly | Q3_K_M (okay) | 15.2 GB | 4.4 GB | ~5 |
| 24 GB VRAM | Runs on GPU | IQ4_XS (good) | 21.0 GB | – | ~32 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 30.2 GB | – | ~39 |
Benchmark results
Epoch AI has not published results for OpenReasoning-Nemotron-32B yet. New models are usually evaluated within days to weeks.
Links
More from NVIDIA
NVIDIA Nemotron Labs Dory1.0 4B BF16 · NVIDIA Nemotron Labs Dory1.0 4B MXFP8 · Nemotron 3.5 Lightning · Nemotron 3 Ultra · Nemotron 3 Super · Nemotron 3-Nano-30B-A3B · Nemotron-Cascade 14B · NVIDIA Isaac GR00T N1.6