available
Weights
7B and 40B model parameters are released.
Inspect this claim’s source ↗Arc Institute and collaborators / FAMILY RECORD
Evo 2
A biological foundation model trained across genomes for sequence understanding and design, released with code, weights, and OpenGenome2 data.
Checked release: Evo 2 7B and 40B
Sources checked 2026-09-19
- Evo 2 release
- · Primary source
The profile describes this checkpoint, not every release carrying the family name. Developer documentation is not independent reproduction.
THE MODEL / THE TERMS
Know what you are picking up.
- Parameters
- 7B and 40B
- Architecture
- StripedHyena 2 sequence model for million-token genomic contexts.
- Modalities
- DNA sequence
- Context
- Up to 1M nucleotides
- Weights license
- Apache-2.0 for code and model artifacts; dataset terms must be checked separately
- Commercial use
- Model code and weights are permissively licensed; biological datasets and downstream applications require separate diligence.
- Memory
- The 40B model is server-class; the 7B model broadens access but still depends on context length and precision.
- Known quantizations
- No canonical quantized release is asserted here
Specifications are developer-reported. Primary release documentation ↗ · All sources and terms
NINE DIMENSIONS / NO OPENNESS SCORE
What is actually available?
Each component has its own evidence. “Not established” means this source review did not verify availability; it is not a claim that nothing exists.
available
Architecture
The paper and code describe StripedHyena 2.
Inspect this claim’s source ↗available
Inference code
Official inference and scoring code is public.
Inspect this claim’s source ↗available
Training code
Pretraining, midtraining and fine-tuning code is released separately in Savanna, as linked by the Evo 2 paper.
Inspect this claim’s source ↗available
Training recipe
The paper documents model and training methodology.
Inspect this claim’s source ↗available
Data information
OpenGenome2 construction is documented.
Inspect this claim’s source ↗available
Training data
OpenGenome2 is released for research use under its stated terms.
Inspect this claim’s source ↗available
Evaluation
The paper publishes biological evaluations and methods.
Inspect this claim’s source ↗partial
Commercial use
Code and weights are permissive, while dataset and application constraints are not reducible to one permission.
Inspect this claim’s source ↗WHY THIS RELEASE MATTERS
What to explore.
- Genomic sequence modeling
- Variant scoring
- Long biological context
- Open data and code
WHAT THE RECORD DOES NOT ESTABLISH
Keep the limits.
- Research model, not a clinical diagnostic
- Generated biological sequences require domain safety review
The peer-reviewed manuscript includes collaborator evaluations; no claim of clinical validation is made.
FOLLOW THE RECORD
Sources, not superlatives.
- Arc Institute Evo 2 announcement ↗ (institution)
- Genome modeling and design across all domains of life with Evo 2 ↗ (paper)
- Savanna training code linked by Evo 2 ↗ (repository)
- Evo 2 repository ↗ (repository)
Source check: 2026-09-19. AI-assisted editorial review, with no named external expert or independent hardware validation claimed. Licenses and model cards can change. Review the linked terms for the specific artifact and intended use.
Understand open source vs open weights ↗