Mamba 2.8B on Replicate API

Mamba · State Spaces

ServerlessOpen Source

Last refreshed 2026-05-19. Next refresh: weekly.

Why use Mamba 2.8B on Replicate API?

Replicate API offers Mamba 2.8B 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 + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "adirik/mamba-2.8b",
    input={"prompt": "Hello"}
Model ID
adirik/mamba-2.8b

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# adirik/mamba-2.8b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "adirik/mamba-2.8b",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • Use provider model ID "adirik/mamba-2.8b", not the LLMReference slug "mamba-2.8b".
  • 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 2.8B

Mamba 2.8B is State Spaces' Mamba model. Its knowledge cutoff is 2020.

Get Started

Model Specs

Released2023-12-01
Parameters2.8B
Context2k
ArchitectureDecoder Only
Knowledge cutoff2020

Related Models on Replicate API