Computational Model Studio · Model release
Mixtral 8x22B Instruct v0.1
Mistral AI instruction-tuned sparse mixture-of-experts model for text responses.
Developer: Mistral AI · Last verified:
What it is designed to do
Generate instruction-following text responses from text prompts; documented tool-call formatting requires an external runtime to execute tools.
Documented uses: Instruction-following chat and formatted tool-call generation.
Access and deployment
- Mixtral 8x22B Instruct v0.1 publisher weights — available. Publisher repository provides public model files for download. Artifact documentation Local hardware requirements have not been verified. Apache License 2.0 (publisher-stated).
Technical profile and review notes
- Construction
- learned
- Representation
- neural
- Normalized architecture tags
- No normalized architecture tag assigned
- Lifecycle
- Unknown from reviewed sources
Inclusion rationale: Adds a publisher-documented sparse mixture-of-experts instruction-tuned release distinct from its base model.
Limitations
- Tool-call text requires a separate runtime to invoke tools; the model does not execute functions by itself.
Sources and related Studio records
Sources
Connections
- In areaComputational Models
- In familyMixtral
- ArtifactMixtral 8x22B Instruct v0.1 publisher weights
- Supports functionGenerate text