SEA-LION v4.8 120B-A12B
SEA-LION v4.8 120B-A12B is available now for long context with open-source and 256K context; evaluate it while provider pricing coverage matures.
No tracked provider pricing is available yet.
About
SEA-LION v4.8 120B-A12B is AI Singapore's larger instruction-tuned Southeast Asian language model, built with NVIDIA on Nemotron 3 Super (Mamba2-Transformer hybrid MoE, about 12B active). AI Singapore reports large SEA-HELM gains over the Nemotron 3 baseline, e.g. Burmese 4.98 to 31.35 and Tamil 21.83 to 56.35. 262,144-token context, MIT license.
Providers
No active provider routes are tracked for this model yet.
Capabilities
No model capability flags are currently sourced.
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.
No tracked provider pricing is available yet.