title: 'Spice Runtime Distributions' sidebar_label: 'Distributions' sidebar_position: 31 description: 'Distribution variants of the Spice runtime for different use cases and deployment scenarios, including data-only, GPU-accelerated, NAS, and allocator variants.' pagination_prev: null pagination_next: null

The Spice open source project provides multiple distribution variants to support different use cases and deployment scenarios.

:::note The Spice runtime is 64-bit only. 32-bit platforms are not supported. :::

Image Channels

:::note Some variant distributions are only available in nightly images (data) or exclusively through the Spice Cloud Platform and Spice.ai Enterprise (opens in a new tab) (NAS, CUDA, allocator variants). :::

Supported Platforms and Hardware Requirements

:::note Windows support is CLI (spice) only. The runtime daemon (spiced) is not supported on Windows natively — use WSL instead. :::

Distribution Availability

Default Distribution

The default distribution includes all features including AI/ML model support. This is the recommended distribution for most users.

Included Features:

• All standard data connectors (PostgreSQL, MySQL, DuckDB, SQLite, ClickHouse, etc.)
• Embedded data accelerators (Spice Cayenne, DuckDB, SQLite)
• AI/ML model inference (LLMs, embeddings)
• Search capabilities (Vector and BM-25 Full-Text-Search)
• Default memory allocator (snmalloc)

:::note The PostgreSQL data accelerator is only available in nightly builds. The PostgreSQL data connector is included in all distributions. :::

Installation:

curl https://install.spiceai.org | /bin/bash

curl https://install.spiceai.org | /bin/bash

Docker:

docker pull ghcr.io/spiceai/spiceai:latest
# or
docker pull spiceai/spiceai:latest

docker pull ghcr.io/spiceai/spiceai:latest
# or
docker pull spiceai/spiceai:latest

Data Distribution

The data distribution excludes AI/ML model support, resulting in a smaller binary size and reduced attack surface. Use this when data federation and acceleration capabilities are needed without AI features.

:::note Open Source: Available in nightly builds only. Cloud Platform & Enterprise (opens in a new tab): Production-ready data distribution available. :::

Included Features:

• The default distribution's data connectors, minus ADBC
• All embedded data accelerators, including the PostgreSQL data accelerator and acceleration snapshots, which the released default binaries do not carry
• Default memory allocator (snmalloc)

Excluded Features:

• AI/ML model inference
• LLM support
• Embedding models

Docker (Nightly):

docker pull ghcr.io/spiceai/spiceai-nightly:latest-data

docker pull ghcr.io/spiceai/spiceai-nightly:latest-data

Local Build:

make install-data-only

make install-data-only

:::note make install-data-only builds from SPICED_DATA_FEATURES in the Makefile — a hand-maintained list that is not the spiced default feature set with models removed, and that differs from it in both directions. Compared with the default distribution it omits the ADBC (opens in a new tab) data connector and the AWS Secrets Manager (opens in a new tab), Azure Key Vault (opens in a new tab) and keyring (opens in a new tab) secret stores, and it adds the PostgreSQL data accelerator (opens in a new tab) and acceleration snapshots (opens in a new tab). The environment (opens in a new tab) and Kubernetes (opens in a new tab) secret stores are not feature-gated and are available in every build.

A feature added to the default set does not reach make install-data-only until it is added to SPICED_DATA_FEATURES too, so recompute the difference from that list and the default = [...] array in bin/spiced/Cargo.toml rather than assuming the two track each other. :::

GPU-Accelerated Distributions

Metal (macOS)

For macOS systems with Apple Silicon, the Metal distribution enables GPU-accelerated AI/ML inference.

Included Features:

• All default features
• Metal GPU acceleration for model inference

Local Build:

make install-metal

make install-metal

CUDA (Linux)

For Linux systems with NVIDIA GPUs, CUDA distributions enable GPU-accelerated AI/ML inference. Multiple CUDA compute capability versions are available.

:::note CUDA distributions are available with the Spice Cloud Platform and Spice.ai Enterprise (opens in a new tab). Open source users can build locally for development and testing. :::

Included Features:

• All default features
• CUDA GPU acceleration for model inference

Supported Compute Capabilities:

• 80 (A100, A30)
• 86 (RTX 30xx, A40, A10)
• 87 (Jetson Orin)
• 89 (RTX 40xx, L40, L4)
• 90 (H100, H200)

Local Build:

CUDA_COMPUTE_CAP=89 make install-cuda

CUDA_COMPUTE_CAP=89 make install-cuda

NFS Distribution

The NFS (Network File System) distribution adds support for the NFS data connector, enabling federated queries against data stored on NFS exports.

:::note The SMB data connector is not part of this variant — smb is in the default spiced feature set, so SMB shares are queryable from the standard distribution. Only the NFS connector is feature-gated. :::

:::note The NFS connector is available with Spice.ai Enterprise (opens in a new tab). Open source users can build locally for development and testing. :::

Included Features:

• All default features
• NFS data connector

Local Build:

make install-nfs

make install-nfs

Allocator Variants

Different memory allocators can significantly impact performance depending on workload characteristics.

:::note Allocator variants are available with the Spice Cloud Platform and Spice.ai Enterprise (opens in a new tab). Open source users can build locally for development and testing. :::

snmalloc (Default)

The default allocator, optimized for concurrent workloads.

jemalloc

Alternative allocator that may perform better for certain memory allocation patterns.

mimalloc

Microsoft's mimalloc allocator, designed for performance and security.

System Allocator

Uses the system's default allocator (glibc malloc on Linux).

Platform Support

:::note Native Windows support for the Spice runtime is available with the Spice Cloud Platform and Spice.ai Enterprise (opens in a new tab). Open source users on Windows should use Windows Subsystem for Linux (WSL). :::

Choosing a Distribution

Additional Connectors

Some connectors require additional dependencies and are available with the Spice Cloud Platform and Spice.ai Enterprise (opens in a new tab):

• ODBC - Connect to any ODBC-compatible data source
• Elasticsearch - Query Elasticsearch indexes with federated SQL

These can be built locally for development and testing:

make install-odbc
make install SPICED_NON_DEFAULT_FEATURES="elasticsearch"

make install-odbc
make install SPICED_NON_DEFAULT_FEATURES="elasticsearch"

Platform-Specific Notes

Linux arm64

• FP16 (FEAT_FP16) is required because the gemm matrix multiplication library (used by the Candle ML framework) contains half-precision ARM inline assembly that requires the fullfp16 CPU feature. This is supported on AWS Graviton2+, Ampere Altra, Apple M-series (via Linux VM), and most ARMv8.2-A+ processors.
• lld is required as the linker because the spiced debug binary is large enough to exceed GNU ld's ±128 MiB branch range for R_AARCH64_CALL26 relocations. lld automatically inserts range extension thunks.
• Install prerequisites on Ubuntu/Debian: sudo apt-get install -y clang lld

Linux x86_64

• Release builds target AVX2+ for optimized SIMD performance, covering Intel Haswell (2013+) and AMD Excavator (2015+) processors, including all current AWS x86_64 instance families (C6/C7/C8).

Building Custom Distributions

Custom distributions with specific feature combinations can be built:

# Build with specific features (replaces the default feature set)
SPICED_CUSTOM_FEATURES="duckdb,postgres,sqlite,models" make build

# Build with non-default features added to defaults
SPICED_NON_DEFAULT_FEATURES="odbc" make install

# Build with specific features (replaces the default feature set)
SPICED_CUSTOM_FEATURES="duckdb,postgres,sqlite,models" make build

# Build with non-default features added to defaults
SPICED_NON_DEFAULT_FEATURES="odbc" make install

See the project Makefile (opens in a new tab) for all available build targets and options.