vllm-sr Decision 3.0 (d3-lite 0.8B, d3-nano 2B, d3-mini 4B) on Core ML for Apple Silicon.
AI & ML interests
None defined yet.
Recent Activity
View all activity
Models specifically tested on Intel's NPU with OpenVINO
-
FluidInference/parakeet-tdt-0.6b-v3-ov
Automatic Speech Recognition • Updated • 48 • 6 -
FluidInference/whisper-large-v3-turbo-fp16-ov-npu
Automatic Speech Recognition • Updated • 22 • 1 -
FluidInference/parakeet-tdt-0.6b-v2-ov
Automatic Speech Recognition • Updated • 24 -
FluidInference/whisper-large-v3-turbo-int8-ov-npu
Automatic Speech Recognition • Updated • 54 • 4
Pre-compiled models for Qualcomm's NPU runtime
Models for Apple devices. See https://github.com/FluidInference/FluidAudio for usage details
-
FluidInference/parakeet-tdt-0.6b-v3-coreml
Automatic Speech Recognition • Updated • 315k • 56 -
FluidInference/parakeet-ctc-110m-coreml
Automatic Speech Recognition • Updated • 93.1k • 2 -
FluidInference/silero-vad-coreml
Voice Activity Detection • Updated • 56.1k • 31 -
FluidInference/speaker-diarization-coreml
Voice Activity Detection • Updated • 28.5k • 44
Collection of MLX models from Fluid Inference
Models tested on Ultra 7+ AIPC GPUs
vllm-sr Decision 3.0 (d3-lite 0.8B, d3-nano 2B, d3-mini 4B) on Core ML for Apple Silicon.
Models for Apple devices. See https://github.com/FluidInference/FluidAudio for usage details
-
FluidInference/parakeet-tdt-0.6b-v3-coreml
Automatic Speech Recognition • Updated • 315k • 56 -
FluidInference/parakeet-ctc-110m-coreml
Automatic Speech Recognition • Updated • 93.1k • 2 -
FluidInference/silero-vad-coreml
Voice Activity Detection • Updated • 56.1k • 31 -
FluidInference/speaker-diarization-coreml
Voice Activity Detection • Updated • 28.5k • 44
Models specifically tested on Intel's NPU with OpenVINO
-
FluidInference/parakeet-tdt-0.6b-v3-ov
Automatic Speech Recognition • Updated • 48 • 6 -
FluidInference/whisper-large-v3-turbo-fp16-ov-npu
Automatic Speech Recognition • Updated • 22 • 1 -
FluidInference/parakeet-tdt-0.6b-v2-ov
Automatic Speech Recognition • Updated • 24 -
FluidInference/whisper-large-v3-turbo-int8-ov-npu
Automatic Speech Recognition • Updated • 54 • 4
Collection of MLX models from Fluid Inference
Pre-compiled models for Qualcomm's NPU runtime
Models tested on Ultra 7+ AIPC GPUs