ALLaM-2-7b instruction tuned model by SDAIA
Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.
| Provider | Provider model ID | Context | Max output | Input | Output | Cache read | Capabilities | Docs |
|---|---|---|---|---|---|---|---|---|
 Groq |
allam-2-7b |
4.096K | 4.096K | — | — | — | Not listed | Docs ↗ |
Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Recorded from the source catalog and provider listings.
sdaia/allam-2-7bWeights: Hugging Face ↗
Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.
Read the methodologyField-level changes detected between successful source imports.
This record has not changed within the retained import history.
Every figure on this page traces back to one of these records.
Fetch the complete source-linked model record. No key, no account, no rate-limited tier.
GET https://www.modelbench.lol/api/v1/models/sdaia/allam-2-7bcurl "https://www.modelbench.lol/api/v1/models/sdaia/allam-2-7b"Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
ALLaM-2-7b instruction tuned model by SDAIA. It is published by Sdaia and catalogued here from Models.dev.
ALLaM-2-7b accepts up to 4.096K tokens of context and returns up to 4.096K output tokens.
1 provider list this model: Groq.
Yes. The weights are published and downloadable from Hugging Face.
The catalog records a release date of 2025-01-23, last verified Aug 04, 2026.