Embla 1

Released
2026-11-13
Last refreshed
2026-11-19
Status
Researched today
Open sourceCommercial use: permittedLong context

Embla 1 is a released long context model with open-source and 256K context; evaluate it while provider pricing coverage matures.

Sevren releases · 1 in the last 12 monthsChangelog →
Specifications
Family
Embla
Released
2026-11-13
Context
256K
Parameters
10B (1B active)
Openness
Open source
License
MITOSI-approvedPermitted
Weights
Available
Code
Unknown
Created by

Sevren is an AI lab developing models for local inference.

Website
Pricing

No tracked provider pricing is available yet.

About

Embla 1 is Sevren’s reasoning language model for phones. It uses mixture-of-experts layers and engram memory, with about 10B total parameters and 1B active per token. Sevren publishes BF16 reference weights and its intended 4-bit phone checkpoint under MIT.

Providers

No active provider routes are tracked for this model yet.

Capabilities

Reasoning

Benchmark peer barsfor Long context

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.