Backend coverage

Aperta
  • Qualcosa non va?
#556 0 commenti 0 reazioni 1 assegnatario Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

@msluszniak ci sta già lavorando.

Dal 26/2/2026.

Valutazione

Questa issue non è ancora stata valutata.

Descrizione

help wanted performance

This task tracks backend coverage across the models wired in the registry.

Regenerated from packages/react-native-executorch/src/models.ts on main plus the Vulkan variants wired in #1479, so it reflects what the library actually resolves rather than what exists on Hugging Face. 104 models across 15 task groups.

Columns

  • CPU (XNNPACK) runs on both platforms; it is the portable fallback and every model has it.
  • Android GPU (Vulkan) is Android only.
  • iOS (Core ML / MLX) is Apple only. Core ML reaches ANE/GPU/CPU; MLX targets Apple Silicon GPU.

Cells list the published precision variants, so 8da4w, fp16 means both are wired. — means the model has no variant for that column.

LLMs
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
LFM2_5_1_2B 8da4w, fp16 — MLX int4
LFM2_5_350M 8da4w, fp16 — MLX int4
LFM2_5_VL_450M 8da4w 8da4w MLX int4
LFM2_5_VL_1_6B 8da4w 8da4w MLX int4, int8
BIELIK_V3_1_5B 8da4w, fp16 — —
LLAMA3_2_1B spinquant, bf16 — MLX int4
LLAMA3_2_3B spinquant, bf16 — MLX int4
SMOLLM2_135M 8da8w — MLX int8
SMOLLM2_360M 8da8w — MLX int8
SMOLLM2_1_7B 8da8w — MLX int8
HAMMER2_1_0_5B 8da4w, bf16 — MLX int4
HAMMER2_1_1_5B 8da4w, bf16 — MLX int4
HAMMER2_1_3B 8da4w, bf16 — MLX int4
PHI4_MINI 8da4w, bf16 — MLX int4
QWEN2_5_0_5B 8da4w, bf16 — MLX int4
QWEN2_5_1_5B 8da4w, bf16 — MLX int4
QWEN2_5_3B 8da4w, bf16 — MLX int4
QWEN3_0_6B 8da4w, bf16 — MLX int4
QWEN3_1_7B 8da4w, bf16 — MLX int4
QWEN3_4B 8da4w, bf16 — MLX int4
GEMMA4_E2B 8da4w 8da4w MLX int4
Text embeddings
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
ALL_MINILM_L6_V2 fp32 fp16 Core ML fp16
ALL_MPNET_BASE_V2 fp32 fp16, int8 —
MULTI_QA_MINILM_L6_COS_V1 fp32 fp16 Core ML fp16
MULTI_QA_MPNET_BASE_DOT_V1 fp32 fp16, int8 —
PARAPHRASE_MULTILINGUAL_MINILM_L12_V2 8da4w, fp32 fp16 Core ML fp16
DISTILUSE_BASE_MULTILINGUAL_CASED_V2 8da4w, fp32 fp16 Core ML fp16 · MLX int8
CLIP_VIT_BASE_PATCH32_TEXT fp32 fp16 Core ML fp16
LFM2_5_EMBEDDING_350M 8da4w — MLX int4
Image embeddings
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
CLIP_VIT_BASE_PATCH32 fp32 fp16 Core ML fp16 · MLX int8
Speech to text
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
WHISPER.TINY fp32 fp16, int8 Core ML fp16 · MLX bf16, int8
WHISPER.BASE fp32 fp16, int8 Core ML fp16 · MLX bf16, int8
WHISPER.SMALL fp32 fp16, int8 Core ML fp16 · MLX int8
WHISPER.EN.TINY fp32, int8 fp16, int8 Core ML fp16 · MLX bf16, int8
WHISPER.EN.BASE int8, fp32 fp16, int8 Core ML fp16 · MLX bf16, int8
WHISPER.EN.SMALL int8, fp32 fp16, int8 Core ML fp16 · MLX int8
Text to speech
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
SUPERTONIC fp32 fp16 MLX fp32
KOKORO.EN_US fp32 — Core ML fp32
KOKORO.EN_GB fp32 — Core ML fp32
KOKORO.ES fp32 — Core ML fp32
KOKORO.FR fp32 — Core ML fp32
KOKORO.IT fp32 — Core ML fp32
KOKORO.PT fp32 — Core ML fp32
KOKORO.HI fp32 — Core ML fp32
KOKORO.PL fp32 — Core ML fp32
KOKORO.DE fp32 — Core ML fp32
Voice activity detection
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
FSMN_VAD fp32 — —
Image classification
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
EFFICIENTNET_V2_S int8, fp32 — Core ML fp16
Object detection
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
SSDLITE320_MOBILENET_V3_LARGE fp32 — Core ML fp16
RFDETR_NANO fp32 fp16 Core ML fp16
YOLO26.NANO.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.NANO.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.NANO.SIZE_640 fp32 fp16 Core ML fp16
YOLO26.SMALL.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.SMALL.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.SMALL.SIZE_640 fp32 fp16 Core ML fp16
YOLO26.MEDIUM.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.MEDIUM.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.MEDIUM.SIZE_640 fp32 fp16 Core ML fp16
YOLO26.LARGE.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.LARGE.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.LARGE.SIZE_640 fp32 fp16 Core ML fp16
YOLO26.XLARGE.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.XLARGE.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.XLARGE.SIZE_640 fp32 fp16 Core ML fp16
Keypoint detection
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
BLAZEFACE fp32 fp16 —
YOLO26_POSE.SIZE_384 fp32 fp16 Core ML fp16
YOLO26_POSE.SIZE_512 fp32 fp16 Core ML fp16
YOLO26_POSE.SIZE_640 fp32 fp16 Core ML fp16
RFDETR_KEYPOINT fp32 fp16 Core ML fp16
Instance segmentation
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
FASTSAM.S fp32 fp16 Core ML fp16
FASTSAM.X fp32 fp16 Core ML fp16
RFDETR_NANO fp32 fp16 Core ML fp16
YOLO26.NANO.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.NANO.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.NANO.SIZE_640 fp32 fp16 Core ML fp16
YOLO26.SMALL.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.SMALL.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.SMALL.SIZE_640 fp32 fp16 Core ML fp16
YOLO26.MEDIUM.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.MEDIUM.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.MEDIUM.SIZE_640 fp32 fp16 Core ML fp16
YOLO26.LARGE.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.LARGE.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.LARGE.SIZE_640 fp32 fp16 Core ML fp16
YOLO26.XLARGE.SIZE_384 fp32 fp16 Core ML fp16
YOLO26.XLARGE.SIZE_512 fp32 fp16 Core ML fp16
YOLO26.XLARGE.SIZE_640 fp32 fp16 Core ML fp16
Semantic segmentation
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
SELFIE_SEGMENTATION fp32 — Core ML fp16
SELFIE_SEGMENTATION_LANDSCAPE fp32 — Core ML fp16
LRASPP_MOBILENET_V3_LARGE int8, fp32 — Core ML fp16
DEEPLAB_V3_RESNET50 int8, fp32 — Core ML fp16
DEEPLAB_V3_RESNET101 int8, fp32 — Core ML fp16
DEEPLAB_V3_MOBILENET_V3_LARGE int8, fp32 — Core ML fp16
FCN_RESNET50 int8, fp32 — Core ML fp16
FCN_RESNET101 int8, fp32 — Core ML fp16
Style transfer
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
CANDY int8, fp32 fp16 Core ML fp16
MOSAIC int8, fp32 fp16 Core ML fp16
RAIN_PRINCESS int8, fp32 fp16 Core ML fp16
UDNIE int8, fp32 fp16 Core ML fp16
OCR
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
PADDLE.PPOCRV6_SMALL yes, fp32 yes Core ML yes
Text to image
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
SDXS_512_DREAMSHAPER fp32 fp16 Core ML fp16
Privacy filter
Model CPU (XNNPACK) Android GPU (Vulkan) iOS (Core ML / MLX)
OPENAI 8da4w — MLX int4
NEMOTRON 8da4w — MLX int8

Notes

  • Vulkan on LFM2.5 is the VL variants only (LFM2_5_VL_450M, LFM2_5_VL_1_6B); the text-only 350M and 1.2B are XNNPACK plus MLX.
  • Published Vulkan exports of EfficientNet, selfie segmentation, LR-ASPP and SSDLite are not wired: each measured slower than the current Android default (#1479).
  • RF-DETR keypoint intentionally has no MLX variant: on an iPhone 16, Core ML fp16 measured 141.6 ms / 248 MB against MLX fp32 at 382.2 ms / 1153 MB, and the MLX delegate has no quantized convolution to close the gap.
  • Core ML text embedders accept a 1-token input as of the seq=1 export fix (react-native-executorch#1164).

References

Lingua principale
TypeScript
Stelle
1.8k
Fork
101
Merge medio
2g 4h
PR unite (30g)
58

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di software-mansion/react-native-executorch

Tutte le issue di software-mansion/react-native-executorch

Issue simili

Altre issue su TypeScript

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.