Rust-native LLM inference for OpenAI-compatible local and private serving.
One binary. No Python runtime. Apple Silicon Metal and NVIDIA CUDA acceleration.
Quick Start
Install the latest stable Ferrum on macOS Apple Silicon or Linux x86_64:
|
The installer verifies release checksums and adds ~/.local/bin to your shell's
PATH. Open a new terminal afterward. Homebrew and manual installation
are also available.
Windows x64 with an NVIDIA sm89 GPU is supported starting with 0.8.9. Install from PowerShell:
irm https://ferrum.pandaailabs.com/install.ps1 | iex
The script verifies the setup checksum, installs for the current user, and adds Ferrum to PATH, including the current PowerShell session.
Inspect the installed binary before downloading weights:
Use the commands for your platform. doctor shows the model-source mapping
without downloading weights or starting the inference engine.
macOS Apple Silicon
The first run downloads about 2.55 GiB. Download time depends on your route to Hugging Face; wait for the progress output before treating the process as hung.
Linux NVIDIA CUDA
The first run downloads about 8.7 GiB of repository weights.
Windows NVIDIA CUDA (0.8.9+)
For a 6GB RTX 4050, use the 2B model with a 2048-token context and one active sequence. The first run downloads the model; these commands preserve its default thinking behavior and allow up to 512 generated tokens:
ferrum doctor Qwen/Qwen3.5-2B
ferrum run Qwen/Qwen3.5-2B --backend cuda --max-model-len 2048 --max-num-seqs 1 --max-tokens 512
To serve it, run:
ferrum serve --model Qwen/Qwen3.5-2B --served-model-name ferrum --backend cuda --max-model-len 2048 --max-num-seqs 1 --port 8000
Then send a request from another PowerShell terminal:
$body = @{ model = 'ferrum'; messages = @(@{ role = 'user'; content = 'Reply with a short hello.' }); max_tokens = 512 } | ConvertTo-Json -Depth 4
Invoke-RestMethod http://localhost:8000/v1/chat/completions -Method Post -ContentType 'application/json' -Body $body
Ferrum does not silently select a model. run requires MODEL, and serve
requires either --model or an intentional default_model in ferrum.toml.
On macOS and Linux, serve the same model through an OpenAI-compatible API:
# macOS Metal
# Linux CUDA
A working request returns HTTP 200 with a non-empty assistant response. Ferrum
uses the model's context limit unless --max-model-len is set explicitly; any
explicit limit must fit the rendered input plus the requested output budget.
The macOS and Linux examples use --disable-thinking so the first response is short and
direct. Omit the flag to preserve the model template's default reasoning
behavior; an HTTP request can override the server default with
chat_template_kwargs.enable_thinking, Chat reasoning_effort, or Responses
reasoning.effort. See reasoning control behavior
for model support and compatibility details.
ferrum doctor <MODEL> resolves an alias and prints the next run and serve
commands without downloading the model or starting an inference engine.
Features
ferrum runandferrum servein one Rust binary.- OpenAI-compatible Chat Completions and stateless Responses APIs, streaming, tools, and structured output.
- Apple Silicon Metal and NVIDIA CUDA from the same runtime.
- Continuous batching, paged KV cache, prefix cache, and typed admission control.
- GGUF on Metal and GPTQ/safetensors on CUDA.
- Ferrum covers language-model inference only. Supported models include Qwen3.5 4B, Qwen3.5 35B-A3B, Qwen3 30B-A3B, and Llama 3.1 8B dense.
Performance Snapshot
Latest R2 development ferrum serve checkpoint. The first three rows use
64-token input / 128-token output on Metal and 256 / 128 on CUDA. Values are
mean tok/s with the 95% confidence-interval half-width across three repeats.
| Model | M1 Max 32 GB Metal | RTX 4090 CUDA | L40S 48 GB CUDA |
|---|---|---|---|
| Qwen3.5 4B | c=16 · 61.9 ± 0.1 | c=32 · 241.3 ± 0.6 | |
| Qwen3.5 35B-A3B | c=4 · 26.1 ± 0.2 | c=16 · 174.1 ± 1.0 | |
| Qwen3 30B-A3B | c=16 · 39.6 ± 1.2 | c=32 · 214.9 ± 2.7 | |
| Qwen3.8 27B AWQ INT4 | c=4 · 78.19 ± 0.04 · c=16 · 115.12 ± 1.18 · c=32 · 115.18 ± 0.97 | ||
| Qwen3.8 27B official block-FP8 | ready 80.91 s · c=1 · 15.23 ± 0.19 · c=8 · 41.75 ± 1.26 · c=32 · 49.75 ± 0.95 | ||
| Qwen3.6 27B official block-FP8 | ready 93.39 s · c=1 · 15.15 ± 0.05 · c=8 · 42.37 ± 3.04 · c=32 · 50.38 ± 0.29 | ||
| Qwen3.6 35B-A3B official block-FP8 | ready 69.62 s · c=1 · 45.01 ± 7.54 · c=8 · 92.78 ± 2.03 · c=32 · 92.78 ± 0.84 | ||
| GPT-OSS 20B official MXFP4 | ready 23.65 s · c=1 · 61.49 ± 4.19 · c=8 · 77.16 ± 0.70 · c=32 · 77.23 ± 4.37 | ||
| Gemma 4 12B official W4A16 CT | ready 24.90 s · c=1 · 9.79 ± 0.01 · c=8 · 52.91 ± 0.88 · c=32 · 66.05 ± 6.78 |
c is active server concurrency. The first three rows completed 100 requests ×
3 repeats with zero errors.
OpenAI-Compatible API
Ferrum supports:
- chat completions and streaming usage
- stateless Responses text, reasoning replay, streaming, usage, and caller-owned function/namespace tool loops
- function tools with
auto,none,required, or a named function json_objectand strictjson_schemastructured output- multi-turn sessions, prefix cache, and session cache
- typed concurrency, memory, and scheduler controls
See OpenAI API compatibility for the exact request contract and cache product controls for prefix and session caching.
Installation
Windows 0.8.9 and later can also be installed by downloading
ferrum-<version>-windows-x86_64-cuda-sm89-setup.exe and its .sha256 file from
Releases, verifying the
checksum, and running setup. It installs under %LOCALAPPDATA%\Programs\Ferrum
and adds the current-user PATH; open a new terminal after a manual setup install.
The package includes CUDA and VC runtimes. It requires a compatible NVIDIA sm89
GPU and driver (551.78 or later); it does not install the system driver or include
models. CUDA Toolkit, Rust, and build tools are not needed. Ferrum remains a
command-line application with run and serve, without a GUI or background service.
To upgrade Windows, rerun the same PowerShell install command or the newer setup. Existing sessions keep running their original version; new launches use the updated version. Models, configuration, and existing version directories are preserved. Restart an existing server when you want it to use the update.
The macOS/Linux one-line installer selects Metal on Apple Silicon. On Linux it selects CUDA for compatible sm89 GPUs when the driver, CUDA 12.4 and NCCL runtimes can load, and otherwise selects CPU. You can require a backend or install a specific version:
|
|
To upgrade an installation made with the script, rerun the original install command. It keeps existing version directories and switches the entry point to the verified new binary. Running sessions continue using their current version; new launches use the new version. Restart an existing server when you want it to use the update. Models and configuration are preserved.
For immediate PATH setup in the current terminal:
For Homebrew installations, use brew upgrade for the installed formula.
Homebrew 6 needs both formula definitions
trusted for its conflict check. Review them before running the trust command;
older Homebrew versions can skip it. See Homebrew's trust documentation.
# Homebrew 6: trust the reviewed formula definitions
# macOS Apple Silicon Metal
# Linux x86_64 CUDA sm89
Prebuilt tarballs from the latest stable release:
# Linux x86_64 CUDA sm89
LD_LIBRARY_PATH=/usr/local/cuda/lib64:
# macOS Apple Silicon Metal
Install the latest Metal build from crates.io:
# macOS Apple Silicon Metal
The official prebuilt Linux CUDA asset targets sm89. Linux CUDA installation requires a
compatible NVIDIA driver, CUDA runtime, and NCCL runtime on the target host.
CUDA source builds also require Ferrum's matching native-operator set, so use
the prebuilt CUDA tarball or Homebrew formula for the supported install path.
Architecture
- Contracts:
ferrum-types,ferrum-interfaces - Execution:
ferrum-engine,ferrum-scheduler,ferrum-kv,ferrum-sampler - Models and compute:
ferrum-models,ferrum-kernels,ferrum-native-ops,ferrum-quantization - Product surface:
ferrum-cli,ferrum-server,ferrum-tokenizer - Validation:
ferrum-bench-core,ferrum-testkit
License
MIT