Kyle PRO

iky1e

2 507 2197

gsaon's profile picture

Tibetan-tts's profile picture

Fishtiks's profile picture

https://ikyle.me

kylehowells

AI & ML interests

None yet

Recent Activity

upvoted a collection 1 day ago

Index-Translate Papers

upvoted a collection 1 day ago

Index-Translate

liked a model 6 days ago

FermionResearch/Phonon-2

View all activity

Organizations

iky1e 's collections 23

Granite Speech 5.0 - Punctuation & Capitalization Model MLX

FP16, Q8, Q6, Q5, and Q4 MLX conversions of 1-800-BAD-CODE/punctuation_fullstop_truecase_english for Granite-MLX. Q8 is the recommended default.

iky1e/punctuation-fullstop-truecase-english-mlx-fp16

Text Classification • 52.3M • Updated Aug 26 • 2
iky1e/punctuation-fullstop-truecase-english-mlx-q8

Text Classification • 14.8M • Updated Aug 26 • 41
iky1e/punctuation-fullstop-truecase-english-mlx-q6

Text Classification • 11.6M • Updated Aug 26 • 5
iky1e/punctuation-fullstop-truecase-english-mlx-q5

Text Classification • 9.96M • Updated Aug 26 • 2

Moebius MLX

MLX conversions of hustvl/Moebius PyTorch inpainting checkpoints, with f32, f16, q8, q4, MXFP, and compact q4 variants.

iky1e/moebius-pretrained-mlx-f32

Image-to-Image • Updated Jun 25
iky1e/moebius-pretrained-mlx-f16

Image-to-Image • Updated Jun 25
iky1e/moebius-pretrained-mlx-q8

Image-to-Image • Updated Jun 25
iky1e/moebius-pretrained-mlx-q4

Image-to-Image • Updated Jun 25 • 1

DeepFilterNet-MLX

MLX ports of the DeepFilterNet speech enhancement models for Apple Silicon

iky1e/DeepFilterNet3-MLX

Audio-to-Audio • 2.17M • Updated Mar 9 • 84 • 6
iky1e/DeepFilterNet2-MLX

Audio-to-Audio • 2.34M • Updated Mar 9 • 22 • 1
iky1e/DeepFilterNet1-MLX

Audio-to-Audio • 1.88M • Updated Mar 9 • 18
mlx-community/DeepFilterNet-mlx

Audio-to-Audio • Updated Mar 11 • 7

Audio Encoder

novateur/WavTokenizer-medium-speech-75token

Updated Sep 19, 2024 • 2
novateur/WavTokenizer-medium-music-audio-75token

Updated Sep 19, 2024 • 6
novateur/WavTokenizer-large-unify-75token

Updated Sep 9, 2024 • 4
novateur/WavTokenizer-large-unify-40token

Updated Oct 22, 2024 • 7

Configuration error

Agents

Featured

4.78k

TRELLIS

🏢

4.78k

Scalable and Versatile 3D Generation from images
Running on Zero

Agents

195

PSHuman

🏃

195

PHOTOREALISTIC HUMAN RECONSTRUCTION w/ CROSS-SCALE DIFF
microsoft/TRELLIS-image-large

Image-to-3D • Updated Dec 6, 2024 • 2.14M • 690
Running on Zero

Agents

Featured

90

GaussianAnything-AIGC3D

🌖

90

Generate 3D models from 2D images

Speech to Text

moonshine-ai/moonshine

Automatic Speech Recognition • Updated Nov 30, 2025 • 98
moonshine-ai/moonshine-tiny

Automatic Speech Recognition • 27.1M • Updated Jan 30, 2025 • 47.4k • 48
moonshine-ai/moonshine-base

Automatic Speech Recognition • 61.5M • Updated Jan 30, 2025 • 25.6k • 48
openai/whisper-large-v3

Automatic Speech Recognition • 2B • Updated Aug 12, 2024 • 4.05M • • 6.57k

Text to Image

Efficient-Large-Model/Sana_1600M_512px_MultiLing

Text-to-Image • Updated Jul 31 • 15 • 16
black-forest-labs/FLUX.1-dev

Text-to-Image • 12B • Updated Jun 27, 2025 • 698k • • 15.4k
black-forest-labs/FLUX.1-schnell

Text-to-Image • 12B • Updated Aug 16, 2024 • 643k • • 6.15k
Freepik/flux.1-lite-8B-alpha

Text-to-Image • 8B • Updated Dec 30, 2024 • 2.64k • 429

structured information extraction

numind/NuExtract-1.5

Text Generation • 4B • Updated May 19 • 2.44k • 249
numind/NuExtract-1.5-tiny

Text Generation • 0.5B • Updated May 19 • 4.01k • • 38
numind/NuExtract-1.5-smol

Text Generation • 2B • Updated May 19 • 334 • 59
HuggingFaceM4/idefics2-8b

Image-Text-to-Text • 8B • Updated Oct 14, 2024 • 75k • 627

Translation

facebook/mbart-large-50-many-to-many-mmt

Translation • 0.6B • Updated Sep 28, 2023 • 74.8k • • 411
facebook/m2m100_418M

Updated Feb 29, 2024 • 436k • 351
facebook/m2m100_1.2B

Updated Nov 16, 2023 • 96.6k • 207
facebook/nllb-200-distilled-600M

Translation • Updated Feb 14, 2024 • 816k • 983

Video Models

genmo/mochi-1-preview

Text-to-Video • 10B • Updated about 1 hour ago • 8.85k • • 1.36k
commanderx/Wav2Lip-HD

Updated Aug 11, 2023 • 48
rain1011/pyramid-flow-miniflux

Text-to-Video • Updated Nov 13, 2024 • 179
briaai/RMBG-2.0

Image Segmentation • 0.2B • Updated Apr 6 • 441k • • 1.5k

Audio Models

ResembleAI/resemble-enhance

Audio-to-Audio • Updated Dec 21, 2023 • 199
fronx/Fast-FullSubNet

Audio-to-Audio • Updated Feb 9, 2024 • 7
tensorlake/segmentation-3.0

Voice Activity Detection • Updated Jul 25, 2024 • 1.01k • 1
tensorlake/speaker-diarization-3.1

Automatic Speech Recognition • Updated Jul 25, 2024 • 1.19k • 4

Image Models

black-forest-labs/FLUX.1-dev

Text-to-Image • 12B • Updated Jun 27, 2025 • 698k • • 15.4k
Running on Zero

Agents

627

AuraSR-v2

😻

627

Upscale images by 4× with a single click
briaai/RMBG-1.4

Image Segmentation • 44.1M • Updated Jul 6, 2025 • 283k • 2.04k
schirrmacher/ormbg

Updated Sep 29, 2024 • 66

Granite Speech 5.0 TurboCTC MLX

Granite Speech 5.0 MLX weights: FP16, Q8, Q6, Q5 and Q4 for both Apache 2.0 and non-commercial model families.

iky1e/granite-speech-5.0-470m-turboctc-mlx-q8

Automatic Speech Recognition • 0.5B • Updated Aug 26 • 81 • 1
iky1e/granite-speech-5.0-470m-turboctc-mlx-fp16

Automatic Speech Recognition • 0.5B • Updated Aug 26 • 48 • 1
iky1e/granite-speech-5.0-470m-turboctc-mlx-q6

Automatic Speech Recognition • 0.5B • Updated Aug 26 • 21 • 1
iky1e/granite-speech-5.0-470m-turboctc-mlx-q5

Automatic Speech Recognition • 0.5B • Updated Aug 26 • 16 • 1

Super-Resolution

One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution

Paper • 2511.17138 • Published Nov 21, 2025 • 2
double8fun/ODTSR

Image-to-Image • Updated Mar 2 • 5
ai-forever/Real-ESRGAN

Updated Sep 25, 2022 • 264
qualcomm/Real-ESRGAN-x4plus

Image-to-Image • Updated 13 days ago • 2.9k • 134

Micro-LLM

xTimeCrystal/MiniModel-200M-Base

Text Generation • 0.2B • Updated Feb 23 • 112 • 30
Qwen/Qwen2.5-0.5B

Text Generation • 0.5B • Updated Sep 25, 2024 • 1.47M • • 463
Qwen/Qwen2.5-0.5B-Instruct

Text Generation • 0.5B • Updated Sep 25, 2024 • 8.43M • • 657
Qwen/Qwen2-0.5B

Text Generation • 0.5B • Updated Oct 22, 2024 • 458k • • 173

Gender Detection

alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech

Audio Classification • 0.3B • Updated Mar 23, 2024 • 542k • 48
audeering/wav2vec2-large-robust-24-ft-age-gender

Audio Classification • 0.3B • Updated Mar 24, 2025 • 2.36M • 62
JaesungHuh/voice-gender-classifier

Audio Classification • 15.5M • Updated May 4, 2025 • 41.5k • 42

Embedding Models

Snowflake/snowflake-arctic-embed-l-v2.0

Sentence Similarity • 0.6B • Updated Jul 28, 2025 • 934k • • 253
allenai/specter2

Updated Dec 4, 2024 • 4.37k • 89
BAAI/bge-large-en-v1.5

Feature Extraction • 0.3B • Updated Feb 21, 2024 • 9.93M • • 747
nomic-ai/modernbert-embed-base

Sentence Similarity • 0.1B • Updated Jan 24, 2025 • 177k • • 234

Audio Analysis

codelion/whisper-age-estimator

Automatic Speech Recognition • 72.6M • Updated Sep 10, 2023 • 19 • 3
blackhole33/uzbek-speaker-verification-v4

Updated May 15, 2024 • 34 • 1
alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech

Audio Classification • 0.3B • Updated Mar 23, 2024 • 542k • 48
fronx/Fast-FullSubNet

Audio-to-Audio • Updated Feb 9, 2024 • 7

Text to Speech

parler-tts/parler-tts-mini-expresso

Text-to-Speech • 0.6B • Updated May 21, 2024 • 362 • 117
parler-tts/parler-tts-large-v1

Text-to-Speech • 2B • Updated Nov 22, 2024 • 8.17k • 275
parler-tts/parler-tts-mini-v1

Text-to-Speech • 0.9B • Updated Nov 25, 2024 • 17.5k • 153
OuteAI/OuteTTS-0.2-500M

Text-to-Speech • 0.5B • Updated Apr 17, 2025 • 163 • 315

Music Models

cvssp/audioldm2-music

0.3B • Updated Apr 16, 2024 • 513 • 29
m-a-p/YuE-s1-7B-anneal-en-cot

Text Generation • 6B • Updated Mar 12, 2025 • 7.61k • 461
HKUSTAudio/YuE-s1-7B-anneal-en-icl

Text-to-Audio • 6B • Updated Jan 29, 2025 • 9 • 21
m-a-p/YuE-upsampler

Text Generation • Updated Mar 12, 2025 • 94 • 25

Open Datasets

neulab/PangeaInstruct

Updated Feb 2, 2025 • 652 • 87
fka/prompts.chat

Viewer • Updated about 1 month ago • 2.17k • 24.1k • 9.85k
PleIAs/common_corpus

Viewer • Updated May 6 • 69.9k • 179k • 429
HuggingFaceTB/smoltalk

Viewer • Updated Feb 10, 2025 • 2.2M • 47.5k • 442

Language Models

oliverguhr/fullstop-punctuation-multilang-large

Token Classification • 0.6B • Updated Nov 16, 2023 • 269k • • 182
google/DiarizationLM-8b-Fisher-v2

8B • Updated Aug 2, 2024 • 770 • 37
unsloth/llama-3-8b-bnb-4bit

Text Generation • 8B • Updated Jan 7, 2025 • 15.8k • 206
openai-community/gpt2

Text Generation • 0.1B • Updated Feb 19, 2024 • 15.2M • 4.2k

Interesting LLM Models

mzbac/llama-3-8B-Instruct-function-calling

Text Generation • 8B • Updated Apr 29, 2024 • 32 • • 30
hjhj3168/Llama-3-8b-Orthogonalized-exl2

Text Generation • Updated May 1, 2024 • 178 • 92
failspy/kappa-3-phi-abliterated

Text Generation • 4B • Updated May 7, 2024 • 53 • 46
failspy/kappa-3-phi-3-4k-instruct-abliterated-GGUF

4B • Updated May 6, 2024 • 33 • 12

Granite Speech 5.0 - Punctuation & Capitalization Model MLX

FP16, Q8, Q6, Q5, and Q4 MLX conversions of 1-800-BAD-CODE/punctuation_fullstop_truecase_english for Granite-MLX. Q8 is the recommended default.

iky1e/punctuation-fullstop-truecase-english-mlx-fp16

Text Classification • 52.3M • Updated Aug 26 • 2
iky1e/punctuation-fullstop-truecase-english-mlx-q8

Text Classification • 14.8M • Updated Aug 26 • 41
iky1e/punctuation-fullstop-truecase-english-mlx-q6

Text Classification • 11.6M • Updated Aug 26 • 5
iky1e/punctuation-fullstop-truecase-english-mlx-q5

Text Classification • 9.96M • Updated Aug 26 • 2

Granite Speech 5.0 TurboCTC MLX

Granite Speech 5.0 MLX weights: FP16, Q8, Q6, Q5 and Q4 for both Apache 2.0 and non-commercial model families.

iky1e/granite-speech-5.0-470m-turboctc-mlx-q8

Automatic Speech Recognition • 0.5B • Updated Aug 26 • 81 • 1
iky1e/granite-speech-5.0-470m-turboctc-mlx-fp16

Automatic Speech Recognition • 0.5B • Updated Aug 26 • 48 • 1
iky1e/granite-speech-5.0-470m-turboctc-mlx-q6

Automatic Speech Recognition • 0.5B • Updated Aug 26 • 21 • 1
iky1e/granite-speech-5.0-470m-turboctc-mlx-q5

Automatic Speech Recognition • 0.5B • Updated Aug 26 • 16 • 1

Moebius MLX

MLX conversions of hustvl/Moebius PyTorch inpainting checkpoints, with f32, f16, q8, q4, MXFP, and compact q4 variants.

iky1e/moebius-pretrained-mlx-f32

Image-to-Image • Updated Jun 25
iky1e/moebius-pretrained-mlx-f16

Image-to-Image • Updated Jun 25
iky1e/moebius-pretrained-mlx-q8

Image-to-Image • Updated Jun 25
iky1e/moebius-pretrained-mlx-q4

Image-to-Image • Updated Jun 25 • 1

Super-Resolution

One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution

Paper • 2511.17138 • Published Nov 21, 2025 • 2
double8fun/ODTSR

Image-to-Image • Updated Mar 2 • 5
ai-forever/Real-ESRGAN

Updated Sep 25, 2022 • 264
qualcomm/Real-ESRGAN-x4plus

Image-to-Image • Updated 13 days ago • 2.9k • 134

DeepFilterNet-MLX

MLX ports of the DeepFilterNet speech enhancement models for Apple Silicon

iky1e/DeepFilterNet3-MLX

Audio-to-Audio • 2.17M • Updated Mar 9 • 84 • 6
iky1e/DeepFilterNet2-MLX

Audio-to-Audio • 2.34M • Updated Mar 9 • 22 • 1
iky1e/DeepFilterNet1-MLX

Audio-to-Audio • 1.88M • Updated Mar 9 • 18
mlx-community/DeepFilterNet-mlx

Audio-to-Audio • Updated Mar 11 • 7

Micro-LLM

xTimeCrystal/MiniModel-200M-Base

Text Generation • 0.2B • Updated Feb 23 • 112 • 30
Qwen/Qwen2.5-0.5B

Text Generation • 0.5B • Updated Sep 25, 2024 • 1.47M • • 463
Qwen/Qwen2.5-0.5B-Instruct

Text Generation • 0.5B • Updated Sep 25, 2024 • 8.43M • • 657
Qwen/Qwen2-0.5B

Text Generation • 0.5B • Updated Oct 22, 2024 • 458k • • 173

Audio Encoder

novateur/WavTokenizer-medium-speech-75token

Updated Sep 19, 2024 • 2
novateur/WavTokenizer-medium-music-audio-75token

Updated Sep 19, 2024 • 6
novateur/WavTokenizer-large-unify-75token

Updated Sep 9, 2024 • 4
novateur/WavTokenizer-large-unify-40token

Updated Oct 22, 2024 • 7

Gender Detection

alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech

Audio Classification • 0.3B • Updated Mar 23, 2024 • 542k • 48
audeering/wav2vec2-large-robust-24-ft-age-gender

Audio Classification • 0.3B • Updated Mar 24, 2025 • 2.36M • 62
JaesungHuh/voice-gender-classifier

Audio Classification • 15.5M • Updated May 4, 2025 • 41.5k • 42

Configuration error

Agents

Featured

4.78k

TRELLIS

🏢

4.78k

Scalable and Versatile 3D Generation from images
Running on Zero

Agents

195

PSHuman

🏃

195

PHOTOREALISTIC HUMAN RECONSTRUCTION w/ CROSS-SCALE DIFF
microsoft/TRELLIS-image-large

Image-to-3D • Updated Dec 6, 2024 • 2.14M • 690
Running on Zero

Agents

Featured

90

GaussianAnything-AIGC3D

🌖

90

Generate 3D models from 2D images

Embedding Models

Snowflake/snowflake-arctic-embed-l-v2.0

Sentence Similarity • 0.6B • Updated Jul 28, 2025 • 934k • • 253
allenai/specter2

Updated Dec 4, 2024 • 4.37k • 89
BAAI/bge-large-en-v1.5

Feature Extraction • 0.3B • Updated Feb 21, 2024 • 9.93M • • 747
nomic-ai/modernbert-embed-base

Sentence Similarity • 0.1B • Updated Jan 24, 2025 • 177k • • 234

Speech to Text

moonshine-ai/moonshine

Automatic Speech Recognition • Updated Nov 30, 2025 • 98
moonshine-ai/moonshine-tiny

Automatic Speech Recognition • 27.1M • Updated Jan 30, 2025 • 47.4k • 48
moonshine-ai/moonshine-base

Automatic Speech Recognition • 61.5M • Updated Jan 30, 2025 • 25.6k • 48
openai/whisper-large-v3

Automatic Speech Recognition • 2B • Updated Aug 12, 2024 • 4.05M • • 6.57k

Audio Analysis

codelion/whisper-age-estimator

Automatic Speech Recognition • 72.6M • Updated Sep 10, 2023 • 19 • 3
blackhole33/uzbek-speaker-verification-v4

Updated May 15, 2024 • 34 • 1
alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech

Audio Classification • 0.3B • Updated Mar 23, 2024 • 542k • 48
fronx/Fast-FullSubNet

Audio-to-Audio • Updated Feb 9, 2024 • 7

Text to Image

Efficient-Large-Model/Sana_1600M_512px_MultiLing

Text-to-Image • Updated Jul 31 • 15 • 16
black-forest-labs/FLUX.1-dev

Text-to-Image • 12B • Updated Jun 27, 2025 • 698k • • 15.4k
black-forest-labs/FLUX.1-schnell

Text-to-Image • 12B • Updated Aug 16, 2024 • 643k • • 6.15k
Freepik/flux.1-lite-8B-alpha

Text-to-Image • 8B • Updated Dec 30, 2024 • 2.64k • 429

Text to Speech

parler-tts/parler-tts-mini-expresso

Text-to-Speech • 0.6B • Updated May 21, 2024 • 362 • 117
parler-tts/parler-tts-large-v1

Text-to-Speech • 2B • Updated Nov 22, 2024 • 8.17k • 275
parler-tts/parler-tts-mini-v1

Text-to-Speech • 0.9B • Updated Nov 25, 2024 • 17.5k • 153
OuteAI/OuteTTS-0.2-500M

Text-to-Speech • 0.5B • Updated Apr 17, 2025 • 163 • 315

structured information extraction

numind/NuExtract-1.5

Text Generation • 4B • Updated May 19 • 2.44k • 249
numind/NuExtract-1.5-tiny

Text Generation • 0.5B • Updated May 19 • 4.01k • • 38
numind/NuExtract-1.5-smol

Text Generation • 2B • Updated May 19 • 334 • 59
HuggingFaceM4/idefics2-8b

Image-Text-to-Text • 8B • Updated Oct 14, 2024 • 75k • 627

Music Models

cvssp/audioldm2-music

0.3B • Updated Apr 16, 2024 • 513 • 29
m-a-p/YuE-s1-7B-anneal-en-cot

Text Generation • 6B • Updated Mar 12, 2025 • 7.61k • 461
HKUSTAudio/YuE-s1-7B-anneal-en-icl

Text-to-Audio • 6B • Updated Jan 29, 2025 • 9 • 21
m-a-p/YuE-upsampler

Text Generation • Updated Mar 12, 2025 • 94 • 25

Translation

facebook/mbart-large-50-many-to-many-mmt

Translation • 0.6B • Updated Sep 28, 2023 • 74.8k • • 411
facebook/m2m100_418M

Updated Feb 29, 2024 • 436k • 351
facebook/m2m100_1.2B

Updated Nov 16, 2023 • 96.6k • 207
facebook/nllb-200-distilled-600M

Translation • Updated Feb 14, 2024 • 816k • 983

Open Datasets

neulab/PangeaInstruct

Updated Feb 2, 2025 • 652 • 87
fka/prompts.chat

Viewer • Updated about 1 month ago • 2.17k • 24.1k • 9.85k
PleIAs/common_corpus

Viewer • Updated May 6 • 69.9k • 179k • 429
HuggingFaceTB/smoltalk

Viewer • Updated Feb 10, 2025 • 2.2M • 47.5k • 442

Video Models

genmo/mochi-1-preview

Text-to-Video • 10B • Updated about 1 hour ago • 8.85k • • 1.36k
commanderx/Wav2Lip-HD

Updated Aug 11, 2023 • 48
rain1011/pyramid-flow-miniflux

Text-to-Video • Updated Nov 13, 2024 • 179
briaai/RMBG-2.0

Image Segmentation • 0.2B • Updated Apr 6 • 441k • • 1.5k

Language Models

oliverguhr/fullstop-punctuation-multilang-large

Token Classification • 0.6B • Updated Nov 16, 2023 • 269k • • 182
google/DiarizationLM-8b-Fisher-v2

8B • Updated Aug 2, 2024 • 770 • 37
unsloth/llama-3-8b-bnb-4bit

Text Generation • 8B • Updated Jan 7, 2025 • 15.8k • 206
openai-community/gpt2

Text Generation • 0.1B • Updated Feb 19, 2024 • 15.2M • 4.2k

Audio Models

ResembleAI/resemble-enhance

Audio-to-Audio • Updated Dec 21, 2023 • 199
fronx/Fast-FullSubNet

Audio-to-Audio • Updated Feb 9, 2024 • 7
tensorlake/segmentation-3.0

Voice Activity Detection • Updated Jul 25, 2024 • 1.01k • 1
tensorlake/speaker-diarization-3.1

Automatic Speech Recognition • Updated Jul 25, 2024 • 1.19k • 4

Interesting LLM Models

mzbac/llama-3-8B-Instruct-function-calling

Text Generation • 8B • Updated Apr 29, 2024 • 32 • • 30
hjhj3168/Llama-3-8b-Orthogonalized-exl2

Text Generation • Updated May 1, 2024 • 178 • 92
failspy/kappa-3-phi-abliterated

Text Generation • 4B • Updated May 7, 2024 • 53 • 46
failspy/kappa-3-phi-3-4k-instruct-abliterated-GGUF

4B • Updated May 6, 2024 • 33 • 12

Image Models

black-forest-labs/FLUX.1-dev

Text-to-Image • 12B • Updated Jun 27, 2025 • 698k • • 15.4k
Running on Zero

Agents

627

AuraSR-v2

😻

627

Upscale images by 4× with a single click
briaai/RMBG-1.4

Image Segmentation • 44.1M • Updated Jul 6, 2025 • 283k • 2.04k
schirrmacher/ormbg

Updated Sep 29, 2024 • 66

Kyle PRO

AI & ML interests

Recent Activity

Organizations

iky1e 's collections 23

TRELLIS

PSHuman

GaussianAnything-AIGC3D

AuraSR-v2

TRELLIS

PSHuman

GaussianAnything-AIGC3D