Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

5,841 builds · page 4 of 98

Ministral-3-8B-Instruct-2512-4bit

from mistralai/Ministral-3-8B-Base-2512
4-bit
Uncategorised · Mistral ↓ 3.6K · ♥ 6
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-12-06

Qwen3.6-35B-A3B-OptiQ-4bit

from Qwen/Qwen3.6-35B-A3B
4-bit
Text generation · Qwen ↓ 3.6K · ♥ 82
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-11-05

Qwen2.5-Coder-3B-Instruct-4bit

from Qwen/Qwen2.5-Coder-3B-Instruct
4-bit
Text generation · Qwen ↓ 3.6K · ♥ 6
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

qwen-research · updated 2024-11-11

SmolLM3-3B-4bit

from HuggingFaceTB/SmolLM3-3B
4-bit
Text generation · Hugging Face ↓ 3.5K · ♥ 7
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-08

Ministral-3-14B-Instruct-2512-4bit

from mistralai/Ministral-3-14B-Base-2512
4-bit
Uncategorised · Mistral ↓ 3.5K · ♥ 3
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-12-03

whisper-turbo

mlx-community/whisper-turbo
Uncategorised ↓ 3.5K · ♥ 8
Params
—
Weights
—
Mac memory
—

updated 2024-10-01

VoxCPM2-bf16

from openbmb/VoxCPM2
bf16
Text to speech · openbmb ↓ 3.4K · ♥ 3
Params
2.4B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-08

gemma-4-31b-it-8bit

from google/gemma-4-31B-it
8-bit
Vision + text · Google · Gemma ↓ 3.4K · ♥ 20
Params
31B
Weights
≈ 33.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-05

Qwen3.6-35B-A3B-5bit

from Qwen/Qwen3.6-35B-A3B
5-bit
Vision + text · Qwen ↓ 3.3K · ♥ 5
Params
35B
Weights
≈ 24.7 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-16

bge-m3-mlx-fp16

from BAAI/bge-m3
fp16
Embeddings · BAAI ↓ 3.2K · ♥ 4
Params
568M
Weights
≈ 1.1 GB
Mac memory
8 GB+

mit · updated 2026-03-16

Qwen3-TTS-12Hz-0.6B-CustomVoice-4bit

mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-4bit
4-bit
Text to speech ↓ 3.2K · ♥ 0
Params
906M
Weights
≈ 1.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-25

Meta-Llama-3.1-8B-Instruct-8bit

mlx-community/Meta-Llama-3.1-8B-Instruct-8bit
8-bit
Text generation ↓ 3.2K · ♥ 10
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.1 · updated 2024-11-26

DeepSeek-R1-0528-Qwen3-8B-4bit

from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
4-bit
Text generation · DeepSeek ↓ 3.2K · ♥ 8
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

mit · updated 2025-05-30

GLM-5.3-Flash-4bit

from zai-org/GLM-5.3-Flash
4-bit
Vision + text · zai-org ↓ 3.2K · ♥ 8
Params
348B
Weights
≈ 206 GB
Mac memory
256 GB+

mit · updated 2026-09-25

Qwen3-ASR-1.7B-4bit

mlx-community/Qwen3-ASR-1.7B-4bit
4-bit
Uncategorised ↓ 3.2K · ♥ 1
Params
2.0B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-29

NVIDIA-Nemotron-3.5-Bolt-E4B-OptiQ-4bit

from nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
4-bit
Vision + text · NVIDIA ↓ 3.2K · ♥ 8
Params
7.5B
Weights
≈ 5.2 GB
Mac memory
8 GB+

openmdw-1.1 · updated 2026-10-24

Qwen3.5-27B-4bit

mlx-community/Qwen3.5-27B-4bit
4-bit
Vision + text ↓ 3.1K · ♥ 50
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-02-24

Breeze-TTS-2-mlx-4bit

from BreezeBlue/Breeze-TTS-2
4-bit
Text to speech · BreezeBlue ↓ 3.1K · ♥ 8
Params
3.5B
Weights
≈ 2.4 GB
Mac memory
8 GB+

breezeblue-research-and-non-commercial-license · updated 2026-08-26

chatterbox-fp16

from ResembleAI/chatterbox
fp16
Text to speech · ResembleAI ↓ 3.1K · ♥ 5
Params
644M
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-05

LFM2.5-VL-1.6B-4bit

from LiquidAI/LFM2.5-1.2B-Base
4-bit
Vision + text · LiquidAI ↓ 3.1K · ♥ 4
Params
1.6B
Weights
≈ 1.5 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-06

Voxtral-4B-TTS-2603-mlx-4bit

from mistralai/Voxtral-4B-TTS-2603
4-bit
Text to speech · Mistral ↓ 3.1K · ♥ 20
Params
4.0B
Weights
≈ 2.5 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2026-03-27

Llama-3.2-3B-Instruct-8bit

mlx-community/Llama-3.2-3B-Instruct-8bit
8-bit
Text generation ↓ 3.0K · ♥ 2
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+

llama3.2 · updated 2024-09-26

Qwen3.5-9B-8bit

from Qwen/Qwen3.5-9B-Base
8-bit
Vision + text · Qwen ↓ 3.0K · ♥ 21
Params
9.4B
Weights
≈ 10.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-02

gemma-4-E4B-it-qat-4bit

mlx-community/gemma-4-E4B-it-qat-4bit
4-bit
Vision + text ↓ 3.0K · ♥ 5
Params
7.9B
Weights
≈ 5.1 GB
Mac memory
8 GB+

updated 2026-06-05

MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit

from XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
4-bit
Text generation · XiaomiMiMo ↓ 3.0K · ♥ 18
Params
9.0B
Weights
≈ 5.0 GB
Mac memory
8 GB+

mit · updated 2026-09-27

whisper-tiny.en-mlx

mlx-community/whisper-tiny.en-mlx
Uncategorised ↓ 3.0K · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2024-03-09

Qwen3-TTS-12Hz-0.6B-CustomVoice-bf16

mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-bf16
bf16
Text to speech ↓ 3.0K · ♥ 2
Params
906M
Weights
≈ 1.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-25

gemma-4-12B-it-OptiQ-4bit

from google/gemma-4-12B-it
4-bit
Text generation · Google · Gemma ↓ 3.0K · ♥ 58
Params
12B
Weights
≈ 6.8 GB
Mac memory
16 GB+

gemma · updated 2026-10-18

chatterbox-turbo-fp16

from mlx-community/chatterbox-turbo-fp16
fp16
Text to speech ↓ 3.0K · ♥ 23
Params
746M
Weights
≈ 3.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-17

DeepSeek-V4.1-Flash-1017-oQ4e-ngram-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017
Vision + text · DeepSeek ↓ 3.0K · ♥ 13
Params
289B
Weights
≈ 506 GB
Mac memory
> 512 GB

mit · updated 2026-10-22

Meta-Llama-3-8B-Instruct-4bit

mlx-community/Meta-Llama-3-8B-Instruct-4bit
4-bit
Text generation ↓ 3.0K · ♥ 84
Params
8.0B
Weights
≈ 5.3 GB
Mac memory
8 GB+

llama3 · updated 2024-04-19

DeepSeek-R1-Distill-Qwen-1.5B-4bit

from deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
4-bit
Uncategorised · DeepSeek ↓ 2.9K · ♥ 7
Params
1.8B
Weights
≈ 1000 MB
Mac memory
8 GB+

updated 2025-02-26

dolphin3.0-llama3.2-3B-4Bit

from dphn/Dolphin3.0-Llama3.2-3B
4-bit
Uncategorised · dphn ↓ 2.9K · ♥ 3
Params
3.2B
Weights
≈ 1.8 GB
Mac memory
8 GB+

llama3.2 · updated 2025-01-22

fish-audio-s2-pro-8bit

from fishaudio/s2-pro
8-bit
Text to speech · fishaudio ↓ 2.9K · ♥ 16
Params
4.6B
Weights
≈ 4.8 GB
Mac memory
8 GB+

fish-audio-research · updated 2026-03-20

MiniMax-M3.1-Flash-Text-3bit

from MiniMaxAI/MiniMax-M3.1-Flash
3-bit
Text generation · MiniMaxAI ↓ 2.9K · ♥ 2
Params
426B
Weights
≈ 186 GB
Mac memory
256 GB+

minimax-community · updated 2026-10-23

Qwen2.5-Coder-32B-Instruct-4bit

from Qwen/Qwen2.5-Coder-32B-Instruct
4-bit
Text generation · Qwen ↓ 2.9K · ♥ 14
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-11-11

Llama-3.2-11B-Vision-Instruct-8bit

from meta-llama/Llama-3.2-11B-Vision-Instruct
8-bit
Vision + text · Meta · Llama ↓ 2.8K · ♥ 9
Params
11B
Weights
≈ 11.3 GB
Mac memory
16 GB+

llama3.2 · updated 2024-10-18

Qwen3.8-27B-mxfp4

from Qwen/Qwen3.8-27B
MXFP4
Vision + text · Qwen ↓ 2.7K · ♥ 10
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-11-11

Qwen3-Coder-Next-8bit

from Qwen/Qwen3-Coder-Next
8-bit
Text generation · Qwen ↓ 2.7K · ♥ 29
Params
80B
Weights
≈ 84.7 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-02-04

Llama-3.2-11B-Vision-Instruct-abliterated

from meta-llama/Llama-3.2-11B-Vision-Instruct
Vision + text · Meta · Llama ↓ 2.7K · ♥ 7
Params
11B
Weights
≈ 21.3 GB
Mac memory
32 GB+

llama3.2 · updated 2024-12-16

Qwen3.6-35B-A3B-bf16

from Qwen/Qwen3.6-35B-A3B
bf16
Vision + text · Qwen ↓ 2.7K · ♥ 11
Params
35B
Weights
≈ 70.2 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-04-16

Qwen2.5-Coder-0.5B-Instruct-4bit

from Qwen/Qwen2.5-Coder-0.5B-Instruct
4-bit
Text generation · Qwen ↓ 2.7K · ♥ 6
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-11

Qwen3.6-27B-8bit

from Qwen/Qwen3.6-27B
8-bit
Vision + text · Qwen ↓ 2.7K · ♥ 20
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-22

DeepSeek-R1-Distill-Qwen-7B-4bit

from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
4-bit
Uncategorised · DeepSeek ↓ 2.7K · ♥ 25
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2025-02-26

gemma-3-4b-it-4bit

from google/gemma-3-4b-pt
4-bit
Vision + text · Google · Gemma ↓ 2.7K · ♥ 8
Params
5.0B
Weights
≈ 3.4 GB
Mac memory
8 GB+

gemma · updated 2025-03-21

csm-1b-8bit

mlx-community/csm-1b-8bit
8-bit
Text to speech ↓ 2.7K · ♥ 2
Params
1.6B
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-05-06

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit

from nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
4-bit
Text generation · NVIDIA ↓ 2.6K · ♥ 7
Params
32B
Weights
≈ 17.8 GB
Mac memory
24 GB+

openmdw-1.1 · updated 2026-08-11

Llama-3.2-3B-Instruct-uncensored-6bit

from chuanli11/Llama-3.2-3B-Instruct-uncensored
6-bit
Text generation · chuanli11 ↓ 2.6K · ♥ 4
Params
3.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+

updated 2025-04-23

Ming-3.0-tts-0.5B-bf16

from inclusionAI/Ming-3.0-tts-0.5B
bf16
Text to speech · inclusionAI ↓ 2.6K · ♥ 0
Params
1.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+

mit · updated 2026-10-22

Phi-4-mini-instruct-4bit

from microsoft/Phi-4-mini-instruct
4-bit
Text generation · Microsoft · Phi ↓ 2.6K · ♥ 5
Params
3.8B
Weights
≈ 2.2 GB
Mac memory
8 GB+

mit · updated 2025-03-05

Qwen3.6-35B-A3B-6bit

from Qwen/Qwen3.6-35B-A3B
6-bit
Vision + text · Qwen ↓ 2.6K · ♥ 11
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-16

GLM-OCR-bf16

from zai-org/GLM-OCR
bf16
Image to text · zai-org ↓ 2.6K · ♥ 31
Params
1.1B
Weights
≈ 2.2 GB
Mac memory
8 GB+

mit · updated 2026-02-04

Llama-3.2-11B-Vision-Instruct-4bit

from meta-llama/Llama-3.2-11B-Vision-Instruct
4-bit
Vision + text · Meta · Llama ↓ 2.6K · ♥ 8
Params
11B
Weights
≈ 6.0 GB
Mac memory
16 GB+

llama3.2 · updated 2024-10-18

gemma-4-31B-it-qat-OptiQ-4bit

from google/gemma-4-31B-it-qat-q4_0-unquantized
4-bit
Text generation · Google · Gemma ↓ 2.6K · ♥ 12
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-18

Qwen3-Embedding-8B-4bit-DWQ

from Qwen/Qwen3-Embedding-8B
4-bit DWQ
Embeddings · Qwen ↓ 2.5K · ♥ 11
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-23

gemma-2-2b-it-4bit

mlx-community/gemma-2-2b-it-4bit
4-bit
Text generation ↓ 2.5K · ♥ 2
Params
2.6B
Weights
≈ 1.5 GB
Mac memory
8 GB+

gemma · updated 2024-11-06

Qwen3.5-4B-bf16

mlx-community/Qwen3.5-4B-bf16
bf16
Uncategorised ↓ 2.5K · ♥ 0
Params
4.5B
Weights
≈ 9.1 GB
Mac memory
16 GB+

updated 2026-03-02

Qwen2.5-VL-7B-Instruct-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Vision + text · Qwen ↓ 2.5K · ♥ 17
Params
8.3B
Weights
≈ 8.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-02-25

Muse-Spark-Open-816B-A42B-oQ3e

from meta-models/Muse-Spark-Open-816B-A42B
3-bit
Vision + text · meta-models ↓ 2.5K · ♥ 7
Params
822B
Weights
≈ 366 GB
Mac memory
512 GB+

muse-model-license · updated 2026-10-16