OLMo-2-0325-32B-Instruct
allenai/OLMo-2-0325-32B-Instruct
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
OLMo · General · OLMo 2
OLMo 2 32B: Specs, GPU requirements, hosting & deployment
OLMo 2 32B is a recent General release in the OLMo family, certified from its immutable official source revision.
Total parameters32.0B
Active parametersDense model
Context window131,072 tokens
Release statusRecent · Recent
ArchitectureDense Transformer
ModalitiesText
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2025-03-12
Architecture, strengths and use cases
OLMo 2 32B is an official self-hostable Allen AI release in the OLMo General track. It uses Dense Transformer, carries 32B, supports a verified context window of 131,072 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
OLMo 2 32B uses Dense Transformer with 32B. The stored architecture profile records 64 layers, hidden width 8192, 64 attention heads and a 131,072 token context ceiling where the official configuration publishes those fields.
Verified Dense Transformer architecture
131,072 token certified context
Official BF16, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed transformers runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory61.39 GB
KV cache2 GB
Runtime overhead16.13 GB
Total with safety margin98.61 GB
Recommended best value
2× NVIDIA A100 SXM 80GB
160 GB total VRAM · nvlink
61.39 GB headroom · Available
USD 1,830 / monthLowest-cost viable
5× NVIDIA L4 24GB
120 GB total VRAM · pcie
21.39 GB headroom · Available
USD 1,250 / monthHighest performance
2× NVIDIA A100 SXM 80GB
160 GB total VRAM · nvlink
61.39 GB headroom · Available
USD 1,830 / monthLicense and self-hosting considerations
The full 32B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
OLMo 2 32B is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
OLMo 3.1 32B Instruct
Release timeline
allenai/olmo/olmo-2-32b
Source details
Source revision: 2ffcf0f2dd7e3031db114c8c22b11fa11a22fdba8cf1717f6b77d9682700c572
Frequently asked questions
How much VRAM does OLMo 2 32B require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support OLMo 2 32B?
Certified upstream runtime evidence is available for transformers.
Can OLMo 2 32B be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.
Official references
Last verified: 2026-08-26