MistralMistral Small 3.2 24B Instruct 2506
Mistral develops the Mistral Small 3.2 24B Instruct 2506, a chat model exceling at following precise instructions and reducing repetition errors, with a notable context window of 131,072 tokens. It demonstrates improved performance in instruction following, achieving a Wildbench v2 score of 65.33% and an IF accuracy score of 84.78%.
Input
Output
Context
131K
Max Output
16K
Parameters
24B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Served variants
The same model in other encodings or serving configurations. Requesting mistral-small-3-2-24b-instruct-2506 lets routing pick among them; the ids below pin one build.
mistral-small-3-2-24b-instruct-2506:fp8quantized
Benchmarks
Estimated GPU requirements for Mistral Small 3.2 24B Instruct 2506
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by Mistral
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Mistral Small 3.2 24B Instruct 2506
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Mistral Small 3.2 24B Instruct 2506 advertises a context window of 131,072 tokens, with a maximum output of 16,384 tokens in a single response. The figure is the creator's published maximum; a given provider may serve less, and the gateway routes on what each provider actually serves.
Yes. Mistral Small 3.2 24B Instruct 2506 is an open-weight model released under the Apache 2.0 license, so the weights can be downloaded and self-hosted within that license's terms.
Mistral Small 3.2 24B Instruct 2506 accepts Text and Image and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
Mistral Small 3.2 24B Instruct 2506 has published results from Artificial Analysis, shown by suite in the benchmarks card above exactly as the publisher reported them. Scores are not combined across suites, and a suite that has not measured Mistral Small 3.2 24B Instruct 2506 is shown as not available rather than estimated.
Yes. Mistral Small 3.2 24B Instruct 2506 is served on the managed pool through the OpenAI-compatible endpoint as mistral-small-3-2-24b-instruct-2506, pinned by name or chosen by routing when it is the best fit for a request. The Try in Playground button opens it directly.
About 24.1 GB at INT8 for the weights and a default context, from the catalog's 24B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, provider APIs and benchmark publishers, each tagged with its source.
Last updated: Nov 6, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start on the free plan with 5,000 requests a month, no card required.