Historical v0.5.3 scope
macMLX v0.5.3
Historically, the 2026-07-08 release expanded compatible APIs, embeddings, model-pool hardening, MCP clients, and the native model stack; later v0.6 work is not part of this record.
Compatibility and upgrade notes
- Compatibility
- API compatibility remains endpoint-specific: Anthropic support is Messages-only, Ollama covers five selected endpoints, and /x/models load and unload routes are macMLX extensions.
- Upgrade
- For this historical release, review the v0.5.3 tagged changelog. Existing clients should keep their documented endpoint and model assumptions; v0.6 batching and prefix reuse are not part of v0.5.3.
Shipped
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
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
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
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
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
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
Bi-encoder rerank MVP
POST /v1/rerank scores independently embedded texts with cosine similarity.
This released MVP is not a cross-encoder reranker.
Verified
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
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
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
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
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
Current limitations
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
Bi-encoder rerank MVP
POST /v1/rerank scores independently embedded texts with cosine similarity.
This released MVP is not a cross-encoder reranker.
Verified
Planned
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
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
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