Current v0.6.2 release

macMLX v0.6.2

The current release completes the v0.6 agent-backend wave and adds Track G model support plus per-model chat-template overrides.

Compatibility and upgrade notes

Compatibility
Model and request boundaries remain explicit: batching is eligibility-gated, structured output rejects unsupported schemas and combinations, and theoretical model tiers do not imply demonstrated generation.
Upgrade
Review the tagged v0.6.2 changelog and model-support guide before upgrading, especially for request compatibility, template precedence, and checkpoint-specific support tiers.

Shipped

Released0.1.0

Apple Silicon macOS installation

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.

Verified

Released0.1.0

Swift in-process inference

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.

Verified

Released0.1.0

Apple Silicon unified memory

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.

Verified

Released0.1.0

Shared code, process-local engines

The app and CLI both import MacMLXCore, which owns inference and the server.

The products share implementation and behavior. When the app and CLI run as separate processes, they do not share one in-memory engine instance.

Verified

Released0.1.0

No Python on the default path

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.

Verified

Released0.5.3

OpenAI endpoint compatibility

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.

Verified

Released0.5.3

Anthropic Messages compatibility

POST /v1/messages, including streaming, is available in v0.5.3.

This is Messages API compatibility only, not compatibility with the full Anthropic API.

Verified

Released0.3.7

Selected Ollama endpoints

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.

Verified

Released0.5.0

MCP server

The CLI can expose local inference to MCP clients.

The MCP server shipped in v0.5.0 and is separate from chat-side routing to external tools.

Verified

Released0.5.3

MCP client pool

v0.5.3 includes managed MCP client connections.

The pool manages external MCP processes and connections; integrated chat-side tool routing is a separate capability released in v0.6.0.

Verified

Released0.6.0

Integrated chat tool routing

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.

Verified

Released0.5.3

Local embeddings

POST /v1/embeddings shipped in v0.5.3.

Encoder-family model detection exists, while using an unsuitable chat model can still produce vectors without semantic guarantees.

Verified

Released0.5.3

Bi-encoder rerank MVP

POST /v1/rerank scores independently embedded texts with cosine similarity.

This released MVP is not a cross-encoder reranker.

Verified

Released0.5.0

Exact-prefix RAM and SSD cache

A hot RAM tier and content-addressed SSD cold tier support promotion and demotion.

The released v0.5.0 cache reuses exact full prefixes. It does not provide released block sharing or paged KV allocation.

Verified

Released0.6.0

Trie longest-prefix reuse

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.

Verified

Released0.5.0

Bounded model pool

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.

Verified

Released0.5.0

Supported LoRA adapters

The native engine can apply supported LoRA adapters.

Adapter compatibility depends on the base architecture and weights; universal LoRA compatibility is not claimed.

Verified

Released0.5.3

Fourteen detected VLM families

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.

Verified

Released0.5.3

DeepSeek V3.2 Swift overlay

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.

Verified

Released0.6.0

Eligibility-gated continuous batching

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.

Verified

Released0.6.0

Fixed prefill admission throttle

A fixed prefillBatchSize bounds rows admitted per scheduler step.

The released throttle is fixed configuration, not the planned adaptive memory controller.

Verified

Released0.6.0

Structured output

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.

Verified

Released0.6.0

Speculative decoding

v0.6.0 ships the classic draft-model path through both the API and GUI.

Acceptance telemetry reports draft efficiency. Targets with non-trimmable hybrid or linear-attention caches are detected and fall back to standard decoding.

Verified

Released0.6.0

API compatibility pack

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.

Verified

Released0.6.0

KV-cache quantization

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.

Verified

Released0.6.0

Hugging Face cache discovery

v0.6.0 can discover models in configured Hugging Face cache roots without downloading duplicate weights.

Discovery confirms a local candidate, not a universal load guarantee; architecture, tokenizer, processor, and checkpoint compatibility still apply.

Verified

Released0.6.2

Per-model chat-template overrides

v0.6.2 resolves templates in user file, built-in model_type, then checkpoint order.

Built-in overrides carry standard-path parity evidence, but template support is not universal; checkpoint-specific branches and unsupported swift-jinja syntax can still define the boundary.

Verified

Released0.6.2

Track G tested models

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.

Verified

Theoretical0.6.2

InternLM3 theoretical support

v0.6.2 ships parity-verified InternLM3 code at the theoretical support tier.

Real generation has not been demonstrated. Public checkpoints ship tokenizer.model but no tokenizer.json, while the Swift tokenizer stack requires tokenizer.json; support remains theoretical until that load-path boundary changes.

Verified

Released0.1.0

Temperature and top-p

Temperature and nucleus top-p sampling are released controls.

These are the current exposed core sampling controls.

Verified

Current limitations

Released0.6.0

Eligibility-gated continuous batching

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.

Verified

Released0.6.0

Structured output

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.

Verified

Theoretical0.6.2

InternLM3 theoretical support

v0.6.2 ships parity-verified InternLM3 code at the theoretical support tier.

Real generation has not been demonstrated. Public checkpoints ship tokenizer.model but no tokenizer.json, while the Swift tokenizer stack requires tokenizer.json; support remains theoretical until that load-path boundary changes.

Verified

Released0.5.3

DeepSeek V3.2 Swift overlay

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.

Verified

Planned

Plannedfuture

Paged KV, block sharing, and CoW

Paged allocation, shared blocks, and copy-on-write branching are planned.

None of these cache-virtualization features is released in v0.6.2.

Verified

Plannedfuture

Unified adaptive memory guard

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.

Verified

Plannedfuture

Expanded sampling controls

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.

Verified

Official sources

  1. macMLX v0.6.2 · github.com
  2. Apple Silicon macOS installation
  3. KV-cache quantization
  4. Apple Silicon unified memory
  5. Selected Ollama endpoints
  6. macMLX v0.6.2 · github.com
  7. MCP client pool
  8. Integrated chat tool routing
  9. Local embeddings
  10. Bi-encoder rerank MVP
  11. Exact-prefix RAM and SSD cache
  12. Trie longest-prefix reuse
  13. Bounded model pool
  14. Track G tested models
  15. DeepSeek V3.2 Swift overlay
  16. Fixed prefill admission throttle
  17. Eligibility-gated continuous batching
  18. Structured output
  19. Speculative decoding
  20. KV-cache quantization
  21. Per-model chat-template overrides
  22. macMLX v0.6.2 · github.com
  23. InternLM3 theoretical support
  24. Temperature and top-p
  25. Expanded sampling controls
  26. Expanded sampling controls