# macMLX questions, answered

Eight v0.6.2 answers covering platform, installation, Python, models, APIs, privacy, vision, large MoE models, and roadmap status.

## Direct answer

These answers use v0.6.2 as the audited baseline and distinguish released capabilities from planned work. API controls retain provider, schema, and combination boundaries; VLM and large-model answers retain checkpoint-specific caveats. Follow the linked technical pages for details. Every visible claim points to dated official evidence.

- Canonical: https://macmlx.app/faq/
- Last verified: 2026-07-15

## Page facts

- **Apple Silicon macOS installation** — Released; since 0.1.0; last verified 2026-07-15. macMLX supports Apple Silicon Macs running macOS 14 or later. Use the current project installation and Gatekeeper guidance; do not disable system-wide security protections solely to open the app.
- **No Python on the default path** — Released; since 0.1.0; last verified 2026-07-15. The released default engine is Swift-native and needs no Python runtime. Optional compatibility engines may use subprocesses and other runtimes. This is not a claim that Python is absent everywhere in the project.
- **Apple Silicon unified memory** — Released; since 0.1.0; last verified 2026-07-15. MLX arrays use the Mac's shared CPU/GPU memory system. Unified memory reduces explicit transfers between CPU orchestration and integrated-GPU compute, but model weights, activations, and KV cache still consume finite physical memory.
- **Bounded model pool** — Released; since 0.5.0; last verified 2026-07-15. Budgets, LRU eviction, pinning, cold swap, idle TTL, and probes bound multi-model use. The pool shipped in v0.5.0 and was hardened in v0.5.3. It is not a unified adaptive controller.
- **Supported LoRA adapters** — Released; since 0.5.0; last verified 2026-07-15. The native engine can apply supported LoRA adapters. Adapter compatibility depends on the base architecture and weights; universal LoRA compatibility is not claimed.
- **Fourteen detected VLM families** — Released; since 0.5.3; last verified 2026-07-15. The model library detects 14 vision-language model_type families. This is an evidence-backed family count, not a guarantee that every checkpoint or processor variant will load.
- **OpenAI endpoint compatibility** — Released; since 0.5.3; last verified 2026-07-15. Chat, legacy completions, model listing, and embeddings use compatible request and response shapes. Compatibility is endpoint-specific. macMLX model load and unload routes under /x/models are project extensions, not OpenAI-compatible model management.
- **Anthropic Messages compatibility** — Released; since 0.5.3; last verified 2026-07-15. POST /v1/messages, including streaming, is available in v0.5.3. This is Messages API compatibility only, not compatibility with the full Anthropic API.
- **Selected Ollama endpoints** — Released; since 0.3.7; last verified 2026-07-15. macMLX supports /api/version, /api/tags, /api/show, /api/chat, and /api/generate. The compatibility layer has shipped since v0.3.7. It is a selected endpoint set, not a drop-in replacement for every Ollama API.
- **Integrated chat tool routing** — Released; since 0.6.0; last verified 2026-07-15. v0.6.0 ships multi-turn tool routing for OpenAI, Anthropic, and the GUI MCP loop. Protocol-specific validation keeps tool-call histories explicit; this routing is distinct from the MCP server and client-pool infrastructure.
- **Structured output** — Released; since 0.6.0; last verified 2026-07-15. v0.6.0 supports response_format with json_object and an explicit JSON Schema subset. Unsupported schema keywords return 400. VLM with structured output and tools with structured output are unsupported combinations and are explicitly rejected rather than silently degraded.
- **API compatibility pack** — Released; since 0.6.0; last verified 2026-07-15. v0.6.0 adds logit_bias, logprobs and top_logprobs, XTC, per-request LoRA adapters, and tools. An explicit compatibility matrix governs parameter combinations, and unsupported pairs return 400 instead of silently degrading.
- **KV-cache quantization** — Released; since 0.6.0; last verified 2026-07-15. v0.6.0 exposes kv_bits, kv_group_size, and quantized_kv_start for compatible requests. These controls change KV-cache precision, not model-weight precision. Nonpositive kv_bits disables the feature, and the compatibility matrix rejects unsupported model or request combinations.
- **Swift in-process inference** — Released; since 0.1.0; last verified 2026-07-15. The default engine loads and runs MLX models inside the Swift process. Model loading, generation, caching, and serving use Apple MLX through MacMLXCore; the default inference path does not require a Python runtime.
- **DeepSeek V3.2 Swift overlay** — Released; since 0.5.3; last verified 2026-07-15. v0.5.3 includes pure-Swift component parity for the DeepSeek V3.2 architecture. A real-checkpoint smoke test remains pending and FP8 dequantization is absent, so this is not an end-to-end or universal MoE claim.
- **Track G tested models** — Released; since 0.6.2; last verified 2026-07-15. v0.6.2 adds four checkpoint-tested native model families. Measured real-checkpoint generation: Seed-OSS-36B 4-bit at 18.2 tok/s; Hunyuan V1 Dense 1.8B 4-bit at 80.3 tok/s; Cohere Command R7B 7B 4-bit at 21.7 tok/s; and MiniCPM3-4B 4-bit at 18.7 tok/s. Results are checkpoint-specific, not family-wide performance guarantees.
- **Eligibility-gated continuous batching** — Released; since 0.6.0; last verified 2026-07-15. v0.6.0 batches only eligible dense-text requests under real concurrency, with automatic serial fallback. The tagged 4-client benchmark measured 2.5–3.2× aggregate throughput. VLM, speculative decoding, Ollama, Anthropic, and embeddings remain serial.
- **Trie longest-prefix reuse** — Released; since 0.6.0; last verified 2026-07-15. v0.6.0 reuses the longest compatible cached token prefix. Multi-turn prompts can trim to the longest common prefix and incrementally prefill only the new suffix while usage retains full-prompt accounting.
- **Paged KV, block sharing, and CoW** — Planned; since future; last verified 2026-07-15. Paged allocation, shared blocks, and copy-on-write branching are planned. None of these cache-virtualization features is released in v0.6.2.
- **Unified adaptive memory guard** — Planned; since future; last verified 2026-07-15. A feedback controller across cache, model pool, and concurrency is planned. Released memory probes and pool caps are separate mechanisms and must not be described as this guard.
- **Expanded sampling controls** — Planned; since future; last verified 2026-07-15. top-k, min-p, presence, frequency, and repetition penalties, plus per-request seed are planned. DeepSeek expert-routing top-k is an internal architecture operation and is unrelated to user sampling top-k.

## Sources

- https://github.com/magicnight/mac-mlx/releases/tag/v0.6.2
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/README.md
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/Engine/MLXSwiftEngine.swift
- https://ml-explore.github.io/mlx/build/html/usage/unified_memory.html
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/CHANGELOG.md
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/ModelPool/ModelPool.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/Managers/ModelLibraryManager.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/Server/HummingbirdServer.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/MCP/ToolCallingSession.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/Constraint/ResponseFormatDecoder.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/Engine/GenerateRequest.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/Models/DeepseekV32.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/docs/model-support.md
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/Batching/BatchScheduler.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/Engine/MLXSwiftEngine+BatchGenerationServing.swift
- https://github.com/magicnight/mac-mlx/blob/v0.6.2/MacMLXCore/Sources/MacMLXCore/PromptCache/PromptTrie.swift
- https://github.com/magicnight/mac-mlx/blob/main/docs/superpowers/specs/2026-07-10-engine-scroll-story-design.md
- https://github.com/magicnight/mac-mlx/blob/main/MacMLXCore/Sources/MacMLXCore/Managers/ModelParametersStore.swift

## Related pages

- [Local API compatibility, endpoint by endpoint](https://macmlx.app/api-compatibility/)
- [Choose models by task and memory](https://macmlx.app/models/)
- [Release status without roadmap blur](https://macmlx.app/releases/)
- [macMLX v0.5.3 (historical)](https://macmlx.app/releases/v0-5-3/)