ml-explore/mlx-examples

View on GitHub

Examples in the MLX framework

Stars: 9k
Forks: 1.2k
Open beginner issues: 0
Indexed issues: 143

Dominant language: Python
License: MIT
Last GitHub push: Apr 6, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

143 open issues indexed

segment_anything: fuse attention with mx.fast.scaled_dot_product_attention Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

ml-explore/mlx-examples#1451 · Opened Sep 7, 2026
Community project: Depth-Anything-V2 running via a from-scratch PyTorch-API shim (torch-mlx) Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

ml-explore/mlx-examples#1449 · Opened Sep 7, 2026
Proposal: neural surface-code decoder (QEC) example? Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1445 · Opened Aug 26, 2026
Suggestion: add a Stable Fast 3D (SF3D) example — native MLX single-image-to-3D-mesh Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

ml-explore/mlx-examples#1443 · Opened Aug 22, 2026
[whisper] `mlx_whisper` CLI overwrites output file when multiple audio inputs are provided Open

Difficulty 2/5 1-3 hours Newbie friendliness 85/100

ml-explore/mlx-examples#1441 · Opened Aug 18, 2026
whisper: numerical parity tests fail with MLX 0.32.0 on Apple Silicon Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

ml-explore/mlx-examples#1440 · Opened Aug 18, 2026
mlx_lm.fuse can not work Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1436 · Opened Aug 6, 2026
Stable Diffusion: Transformer2D's GroupNorm uses MLX's default eps (1e-5) where diffusers uses 1e-6 Open

Difficulty 1/5 Under an hour Newbie friendliness 84/100

ml-explore/mlx-examples#1434 · Opened Jul 31, 2026
[Proposal] DeepSeek-OCR example — SAM + CLIP dual vision encoder → DeepSeek-V2 MoE Open

Difficulty 5/5 Over a week Newbie friendliness 32/100

ml-explore/mlx-examples#1433 · Opened Jul 30, 2026
whisper: align no_speech_threshold fallback condition with openai/whisper Open

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

ml-explore/mlx-examples#1427 · Opened Jun 18, 2026
whisper/convert.py outputs `model.safetensors` but `mlx_whisper.load_models` expects `weights.safetensors` Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

ml-explore/mlx-examples#1421 · 1 comment · Opened May 1, 2026
[whisper] `KeyError: 'words'` on transcription (with `--task translate`) Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

ml-explore/mlx-examples#1418 · Opened Apr 24, 2026
[whisper] Add Flash Attention and batched decoding for up to 10x speedup Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx-examples#1412 · 3 comments · 1 reaction · Opened Mar 26, 2026
[whisper] Feature Request: Add `carry_initial_prompt` parameter to `transcribe()` Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

ml-explore/mlx-examples#1410 · 1 reaction · Opened Mar 13, 2026
[Model Request] Porting Nvidia PersonaPlex-7B (Moshi architecture) & Mimi Codec Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1405 · 1 comment · Opened Feb 12, 2026
Question: (mlx_whisper) How to eliminate spurious "you" transcriptions Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1402 · 1 comment · Opened Dec 24, 2025
Using fine tuned whisper models in MLX must support beam search Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1391 · 1 reaction · Opened Nov 6, 2025
How to fine tune quantized modeling convert it to GGUF still been quantized? Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1382 · 1 reaction · Opened Aug 14, 2025
Support for Qwen-Image generation Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1379 · 2 comments · 4 reactions · Opened Aug 4, 2025
Convert method for only for pytorch/safetensors to MLX Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx-examples#1374 · Opened Jul 21, 2025
Is there a way to implement a Timeout / cancellation for transcribe() method, espeicially model.decode()? (large-v3 sometimes stalls >200s on ~10s audio) Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx-examples#1373 · 1 comment · Opened Jul 18, 2025
Segfault during inference Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1368 · 4 comments · Opened Jun 4, 2025
mlx-whisper OOM error on files > 1GB Open

Difficulty 4/5 3-5 days Newbie friendliness 32/100

ml-explore/mlx-examples#1366 · 4 comments · Opened May 5, 2025
text to video model support? Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

ml-explore/mlx-examples#1335 · 6 reactions · Opened Mar 11, 2025
Possible to reduce disc writes when converting models? Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1320 · 4 comments · Opened Mar 4, 2025
UserWarning: mlx_lm.server is not recommended for production as it only implements basic security checks. Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

ml-explore/mlx-examples#1310 · 2 reactions · Opened Feb 27, 2025
How to get the logits in mlx-lm? Open

Difficulty 3/5 1-2 days Newbie friendliness 38/100

ml-explore/mlx-examples#1292 · 2 comments · Opened Feb 20, 2025
MiniMax-Text-01 Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1290 · 7 comments · Opened Feb 17, 2025
Unexpected processing times for short vs. long audio files with mLX-whisper with clip_timestamps enabled Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

ml-explore/mlx-examples#1285 · Opened Feb 14, 2025
Poor Speculative Decoding Performance on M2 Ultra Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1281 · 4 comments · Opened Feb 12, 2025
mlx_lm.batch Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1268 · 2 comments · Opened Feb 9, 2025
mlx to GGUF Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1261 · 2 reactions · Opened Feb 8, 2025
Higher Speed High-Context processing w/ Minference Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1245 · 2 reactions · Opened Feb 4, 2025
[Feature] Continue fine-tuning after the training has been interrupted Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx-examples#1237 · 1 comment · 2 reactions · Opened Feb 1, 2025
Running larger MobileCLIP and AIMv2 on MLX Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1227 · Opened Jan 27, 2025
Failing when trying to run DeepSeek-R1-3bit on 3 Studios M2 Ultra with 128GB RAM each Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

ml-explore/mlx-examples#1226 · 2 comments · Opened Jan 26, 2025
Improve support for customizing the LoRa train method Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1224 · 1 comment · 1 reaction · Opened Jan 26, 2025
How to convert Falcon models Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

ml-explore/mlx-examples#1223 · 2 comments · Opened Jan 24, 2025
Distributed only utilizing the GPU on the host machine Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

ml-explore/mlx-examples#1218 · 9 comments · Opened Jan 21, 2025
Concurrent requests Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1198 · 1 comment · 8 reactions · Opened Jan 9, 2025
mlx_lm support for Bloom models Open

enhancement

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1187 · 1 comment · Opened Jan 2, 2025
mlx_lm with llama-3.3-70b-instruct works like base model in some case. Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

ml-explore/mlx-examples#1162 · 3 comments · Opened Dec 15, 2024
[Feature Request] Unable to Unload or Swap adapters at runtime Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx-examples#1108 · 2 comments · Opened Nov 18, 2024
Whisper transcribing music sounds Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1101 · 2 comments · Opened Nov 9, 2024
Support for AI21 Jamba-1.5 Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1097 · 1 comment · 3 reactions · Opened Nov 7, 2024
[Feature Request] Custom "chat" HF datasets Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1088 · Opened Nov 3, 2024
load_custom_hf_dataset not handling the text_feature argument properly Open

Difficulty 2/5 1-3 hours Newbie friendliness 45/100

ml-explore/mlx-examples#1087 · Opened Nov 3, 2024
Llama-3.1-8B-Instruct-4bit keeps looping at the end. Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1059 · 33 comments · Opened Oct 21, 2024
Musicgen Duration, Stereo, Melody Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-examples#1058 · 1 comment · 1 reaction · Opened Oct 21, 2024
[FEATURE REQUEST] Support for LLM2VEC Encoder-Decoder LLMs Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-examples#1052 · 2 reactions · Opened Oct 16, 2024

ml-explore/mlx-examples

Get new issues in your inbox