Last refreshed 2026-05-01. Next refresh: weekly.
Why use Marin 8B Instruct on NVIDIA NIM?
NVIDIA NIM offers Marin 8B Instruct with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: marin/marin-8b-instructModel ID
marin/marin-8b-instructRequest example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
marin/marin-8b-instruct.Gotchas
- Use provider model ID "marin/marin-8b-instruct", not the LLMReference slug "marin-8b-instruct".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
No model capability flags are currently sourced.
About Marin 8B Instruct
Marin 8B instruction-tuned model from Stanford CRFM focused on interpretability.
FAQ
What is the context window for Marin 8B Instruct on NVIDIA NIM?
Marin 8B Instruct supports a 128,000 token context window on NVIDIA NIM.
What API model ID do I use for Marin 8B Instruct on NVIDIA NIM?
Use the model ID marin/marin-8b-instruct when calling NVIDIA NIM's API.
Who created Marin 8B Instruct?
Marin 8B Instruct was created by Marin as part of the Marin model family.
Is Marin 8B Instruct open source?
Marin 8B Instruct is open source according to the seed data.
Model Specs
Released2025-09-01
Parameters8B
Context128K
ArchitectureDecoder Only