Local-first MLX serving
Run MLX models entirely on device with project-owned endpoints and artifacts.
你的 Mac。你的 MLX 模型。一条可度量工作流。
Melix 把分散的本地 AI 工作变成 Apple Silicon 上的一套可重复 studio。
本地服务模型，用 LoRA 调优，严谨 benchmark，评测并导出。没有云端，没有订阅，数据不离开你的 Mac。
- 原生 macOS app + CLI
- 面向 Apple Silicon 优化
- 100% 本地
- 无订阅
LoRA fine-tuning
Parameter-efficient tuning with repeatable local runs and adapter records.
Benchmark comparison
Track performance across MLX models, configs, datasets, and hardware.
Evaluation artifacts
Generate reports and exports that make local model changes auditable.
MLX Model Registry
| Model | Type | Size | Updated |
|---|---|---|---|
| mlx-community/Mistral-7B-Instruct-v0.3 | MLX | 4.2 GB | Jun 8 |
| mlx-community/Llama-3.2-3B-Instruct | MLX | 2.4 GB | Jun 7 |
| mlx-community/Qwen2.5-Coder-7B-Instruct | MLX | 4.7 GB | Jun 6 |
| support-tone-lora-r16 | LoRA | 184 MB | Jun 5 |
| mlx-community/Phi-3.5-mini-instruct | MLX | 2.2 GB | Jun 4 |
Active Local Server
Running- Model
- Mistral-7B-Instruct-v0.3
- Runtime
- MLX / Metal
- Endpoint
- localhost:11434/v1
- Context
- 4096
- Requests
- 1,248
Benchmarks / Evaluation
| Model | Score | 95% CI |
|---|---|---|
| Mistral-7B-Instruct-v0.3 | 8.48 | +/- 0.12 |
| Qwen2.5-Coder-7B-Instruct | 8.17 | +/- 0.15 |
| Llama-3.2-3B-Instruct | 7.83 | +/- 0.13 |
| Phi-3.5-mini-instruct | 6.91 | +/- 0.14 |
-
$ melix models add --source mlx Mistral-7B-Instruct-v0.3Model registry -
$ melix serve --runtime mlx --model Mistral-7B-Instruct-v0.3Local server -
$ melix lora train --config tone.ymlLoRA training -
$ melix benchmark run --suite mt-benchBenchmark -
$ melix eval export --format report.md,jsonEvaluation export
why local
Local execution changes the development loop.
Local execution by default
Run model serving, adapter tuning, benchmarks, and evaluations on your Mac. Keep prompts, adapters, benchmark outputs, and eval artifacts in a local workflow.
Fast iteration
Serve a model, test an adapter, run an evaluation, and compare results without waiting on hosted inference queues or remote experiment infrastructure.
Reproducible workflow state
Track the model, target hardware, adapter, benchmark settings, eval set, and output metrics behind each run.
工作流 ledger
从模型到度量的一条本地工作流。
服务模型、挂载 adapter、benchmark 运行、评测输出，并在本地检查证据。
technical surface
Built like a datasheet, not a promise deck.
Runtime
- MLX model contexts
- Metal-targeted local execution
- localhost endpoints for app loops
LoRA
- adapter rank and checkpoint ledger
- dataset locality by project path
- serve-time adapter comparison
Measurement
- tokens/sec and p95 latency
- memory and run deltas
- offline eval-set regression checks
See the proof
Independent benchmarks and real results from local Apple Silicon hardware.
View Benchmarks- MT-Bench
- 8.48 Mistral-7B-Instruct-v0.3 on Mac Studio
- Arena Hard
- 58.3% win rate for top local run
- Tokens / sec
- 112.6 at 4k context
- Runs
- 247 across 12 datasets and 6 models
Built for local MLX operators
Choose the local loop you run most often.
Build local apps
Wire local MLX serving into app loops.
local endpoint, request log, reproducible run state
Tune and compare models
Train LoRA and compare adapters.
score deltas, latency, adapter artifacts
Evaluate private research
Test prompts and models without remote services.
markdown/json exports, local dataset path, no data leaves Mac
Docs
Everything you need in one local studio
Roadmap
A native MLX studio for the full Apple Silicon loop.
Melix is moving toward richer runtime operations, stronger evaluation workflows, better packaging, and more native operator polish.
status
Alpha software for local-first builders.
Melix is early, explicit, and local-first. The product is built around a concrete developer workflow: serve the model on your Mac, tune or attach an adapter, benchmark the run, evaluate the output, and inspect the evidence locally.
Inspect the repository