Reference · rapid-mlx 0.10.3 · ← Back to README

Model aliases

Rapid-MLX ships 158 text aliases plus a separate audio registry (kokoro / whisper / parakeet / vibevoice / voxcpm / chatterbox / dia). An alias is a short, stable name that resolves to a canonical HuggingFace MLX repo and auto-applies the right tool-call parser, reasoning parser, hybrid-cache flag, MoE flag, spec-decode eligibility, and PFlash tier.

Source of truth. The text-alias registry lives at vllm_mlx/aliases.json in the engine repo (audio lives at vllm_mlx/audio/aliases.json). The table on this page mirrors what rapid-mlx models prints in 0.10.3.

Naming convention

Every text alias follows the same template:

<family>-<version>-<params>-<modality?>-<technique?>-<quant>
SegmentMeaningExamples
familyModel familyqwen, gemma, llama, mistral, deepseek, phi, hermes
versionMajor version3.5, 3.6, -4, -r1, -v4-flash
paramsParameter count (MoE includes active)4b, 12b, 27b, 35b-a3b (35B total / 3B active)
modality (optional)Non-text variants-vl (vision), -coder (code)
technique (optional)Training-time modifier-qat (QAT), -distill, -thinking, -assistant (MTP assistant drafter)
quant (mandatory)Quantization tier-4bit, -6bit, -8bit, -mxfp4, -mxfp4-q8, -qat-4bit

The quant suffix is mandatory on every alias — qwen3.5-4b-4bit, not qwen3.5-4b. This mirrors the LM Studio …-MLX-4bit HuggingFace convention. -qat is a technique suffix, not a quant — it stacks before the quant, so a QAT-trained Gemma 4 12B at 4-bit is gemma-4-12b-qat-4bit.

Registry schema

Every text entry in aliases.json is a closed dict with a fixed key set. Adding an unknown key (e.g. architecture, family, quantization, or notes) will fail alias loading — copy the field set from the closest existing neighbour when adding a new alias.

KeyTypeMeaning
hf_pathstringHuggingFace repo id in org/name form. The only mandatory field.
tool_call_parserstringWhich tool-call parser to auto-select at serve time (hermes, qwen3_coder, gemma4, harmony, deepseek, …).
reasoning_parserstringWhich reasoning parser to auto-select (qwen3, gemma4, deepseek_r1, gpt_oss, harmony, vibethinker, glm4, minimax, ui_tars).
is_hybridboolHybrid-attention (Mamba / linear-attention / DiffusionGemma / Granite 4 H) — disables spec-decode / suffix.
is_hybrid_explicitboolWhether the hybrid flag was set intentionally (as opposed to defaulted).
is_moeboolMixture-of-experts model.
supports_spec_decodeboolWhether spec-decode routes are eligible.
pflash_tierstringPFlash long-prompt compression tier — verified, unknown, avoid, neutral, n/a.

What rapid-mlx models prints

The rapid-mlx models table has 7 columns. Column semantics match the schema fields above:

ColumnMeaning
AliasThe short name you pass to serve / chat / pull.
ToolsTool-call parser that will be auto-selected (or ).
ReasoningReasoning parser that will be auto-selected (or ).
Spec-Decode when spec-decode is eligible; ✗ hybrid when a hybrid architecture rules it out; when the alias opts out.
Suffix TierSuffix-decoding recommendation: verified, neutral, avoid, unknown, n/a.
DFlashDFlash drafter registry status ( when no registered drafter for this alias).
DDTreeDDTree runtime status ( when not enabled).

Run rapid-mlx models locally for the live view — the browse-friendly UI at models.rapidmlx.com renders the same data as a filterable grid.

Text families in 0.10.3

158 text aliases across the following families (count from a byte-exact read of vllm_mlx/aliases.json):

Family# aliasesNotes
Qwen 3 (3.5 · 3.6 · Coder · VL · legacy)50Anchor family — includes MoE 35B-A3B / 122B, hero coder alias, VL variants.
Gemma 4 (dense · e2b / e4b · qat · assistant · optiq · DiffusionGemma)27Includes 3 DiffusionGemma / EmbeddingGemma aliases.
GPT-OSS (20B · 120B · MXFP4-Q4/Q8 · safeguard)10Harmony-native tool + reasoning parsers.
UI-TARS9ByteDance vision-grounded UI automation agent. Custom ui_tars tool parser.
Tmax (9B / 27B, 4/6/8-bit + bf16)7Hybrid Gated-DeltaNet agent model (Ai2). First-mover MLX quants.
DeepSeek (R1-Distill · V4-Flash 2/4/8bit · Coder-V2-lite)6V4-Flash is single-node-large; R1-Distill covers the 32B slot.
Gemma 3 (1B–27B · qat)6Kept for continuity; new work targets Gemma 4.
Phi 4 (mini + mini-flash 4bit variants)4
Mistral (7B / 24B · Devstral · Ministral)4 + 2 + 1Devstral is the code variant; Ministral is the small chat SKU.
Qwopus3Community fork lineage.
Bonsai3Small hybrid-attention reasoners.
GLM 4 (Air · 4.7)2 + 1Plus one GLM-5.2 REAP-50 entry (research SKU).
Llama (3.1 · 3.2)2 + 2
MiniMax (M2.5 / M2.7 MXFP4)2Uses the minimax parser pair.
Granite 4 (H-Micro / Tiny)2Hybrid architecture; spec-decode disabled.
VibeThinker (1.5B / 3B)2Low-RAM reasoner — 4-bit fits a 4 GB Mac.
Holo32Hybrid MoE 35B-A3B; operator-owned deployment target.
Hermes 3 · 41 + 1
Others (Kimi K2.6 · Qwen 2 · Nemotron 3 · SmolLM3 · Nanbeige 4)5One alias each.

Audio registry

Audio aliases live in a separate registry — start them the same way: rapid-mlx serve whisper-large-v3. Registered in 0.10.3:

KindAliases
TTS · kokorokokoro, kokoro-82m, kokoro-82m-bf16, kokoro-82m-4bit, kokoro-82m-8bit, kokoro-4bit, kokoro-8bit
TTS · vibevoice / voxcpm / chatterbox / diavibevoice, vibevoice-realtime, voxcpm, chatterbox, chatterbox-4bit, dia
STT · whisperwhisper, whisper-1, whisper-large-v3, whisper-large-v3-turbo, whisper-medium, whisper-small, whisper-base, whisper-tiny
STT · parakeetparakeet, parakeet-tdt-0.6b, parakeet-tdt-0.6b-v2, parakeet-v3, parakeet-tdt-0.6b-v3

Audio requires the [audio] extra — pip install "rapid-mlx[audio]==0.10.3". See the extras page for the full dep list.

The (unmapped) column

rapid-mlx ls (aka models --cached) shows every HF repo already on disk. Repos that have no matching alias in aliases.json render as (unmapped) in the Alias column — you can still serve them by their full org/name HF path (e.g. rapid-mlx serve mlx-community/Holo3-35B-A3B-8bit).

Next steps