Last refreshed 2026-04-19. Next refresh: weekly.
Why use Mamba 790M on Replicate API?
Replicate API offers Mamba 790M with competitive pricing. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"mamba-790m",
input={"prompt": "Hello"}Model ID
mamba-790mRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# mamba-790m format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"mamba-790m",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
- The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.
Capabilities
No model capability flags are currently sourced.
About Mamba 790M
Compact Mamba state-space model for efficient inference.
FAQ
Who created Mamba 790M?
Mamba 790M was created by State Spaces as part of the Mamba model family.
Is Mamba 790M open source?
Mamba 790M's open source status is unknown in the seed data.
Get Started
Model Specs
Released2023-12-01
Parameters790M
ArchitectureDecoder Only