Latest Content
Olmo 3.1 32B Instruct icon

Olmo 3.1 32B Instruct

NVIDIA
Olmo 3.1 32B Instruct is a dense transformer language model and a successor to Olmo 3, designed for strong instruction following, chat, and multi-turn agentic workflows. It is built on a 32B parameter architecture with 64 layers, 5,120 hidden size, and 40 attention heads, using grouped query attention with 8 key-value heads for efficient inference. The model supports up to a 65K context window with YaRN-based RoPE scaling and combines sliding window attention with a 4K window and periodic full attention layers for improved long-context handling. Fine-tuned using supervised learning and extended reinforcement learning training, it delivers strong performance on reasoning, coding, and complex multi-step tasks.
TypeDense LLM
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+4 more
Release Date15 December, 2025
Links
Paper|Blog|HF Model Card
LicenseApache 2.0

Inference Instructions

Deploy and run this model on NVIDIA B200 GPUs using the command below. Copy the command to get started with inference.

CONSOLE
docker run --gpus all 
 --shm-size 128g 
 --cap-add SYS_NICE 
 -p 8000:8000 
 -v ~/.cache/huggingface:/root/.cache/huggingface 
 -e HF_TOKEN='YOUR_HF_TOKEN' 
 --ipc=host 
 lmsysorg/sglang:v0.5.9 
 python3 -m sglang.launch_server 
 --model-path allenai/Olmo-3.1-32B-Instruct 
 --host 0.0.0.0 
 --port 8000 
 --max-prefill-tokens 65536 
 --tool-call-parser pythonic  
 --max-running-requests 1024 
 --tp 8 
 --mem-fraction-static 0.95 
 --trust-remote-code
Note

Use the --tool-call-parser pythonic flag to handle OLMo 3.1's native syntax and omit --enable-piecewise-cuda-graph to prevent hangs during the CUDA graph capture phase.

Model Benchmarks

Each model was tested with a fixed input size and total token volume while increasing concurrency to measure serving performance under load.

ITL vs Concurrency

Time to First Token

Throughput Scaling

Total Tokens/sec vs Avg TTFT

Vultr Cloud GPU

NVIDIA HGX B200

Deploy NVIDIA B200 on Vultr Cloud GPU

Deploy NVIDIA B200 instancesContact Sales