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 27 of 98

Hermes-3-Llama-3.1-70B-4bit

from meta-llama/Llama-3.1-70B
4-bit
Uncategorised · Meta · Llama ↓ 153 · ♥ 3
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+

llama3 · updated 2024-08-16

Nemotron-Cascade-2-30B-A3B-nvfp4

from nvidia/Nemotron-Cascade-2-30B-A3B
4-bit
Text generation · NVIDIA ↓ 153 · ♥ 1
Params
32B
Weights
≈ 17.8 GB
Mac memory
24 GB+

nvidia-open-model-license · updated 2026-04-30

Skyfall-31B-v4.2-heretic-mlx-8Bit

from coder3101/Skyfall-31B-v4.2-heretic
8-bit
Uncategorised · coder3101 ↓ 153 · ♥ 1
Params
31B
Weights
≈ 33.3 GB
Mac memory
48 GB+

updated 2026-08-06

Qwopus3.8-27B-Flash-mxfp8-MLX

from Jackrong/Qwopus3.8-27B-Flash
MXFP8
Vision + text · Jackrong ↓ 153 · ♥ 0
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-09-14

deepseek-coder-7b-base-v1.5-4bit-MLX-skirano

mlx-community/deepseek-coder-7b-base-v1.5-4bit-MLX-skirano
4-bit
Uncategorised ↓ 153 · ♥ 0
Params
6.9B
Weights
≈ 4.5 GB
Mac memory
8 GB+

deepseek-license · updated 2024-01-31

diffusiongemma-26B-A4B-it-mxfp4

from google/diffusiongemma-26B-A4B-it
MXFP4
Vision + text · Google · Gemma ↓ 152 · ♥ 6
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-15

GLM-4-32B-0414-4bit

from THUDM/GLM-4-32B-0414
4-bit
Text generation · THUDM ↓ 152 · ♥ 4
Params
33B
Weights
≈ 18.3 GB
Mac memory
24 GB+

mit · updated 2025-04-21

gemma-4-26B-A4B-it-qat-nvfp4

mlx-community/gemma-4-26B-A4B-it-qat-nvfp4
4-bit
Vision + text ↓ 152 · ♥ 3
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

updated 2026-06-05

Apertus-8B-Instruct-2509-4bit

from swiss-ai/Apertus-8B-Instruct-2509
4-bit
Text generation · swiss-ai ↓ 152 · ♥ 1
Params
8.1B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-09-03

Kestrel-4B-Coder-8bit

from unsloth/Qwen3.5-4B
8-bit
Vision + text · unsloth ↓ 152 · ♥ 0
Params
4.5B
Weights
≈ 5.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-07

Qwopus3.8-27B-Flash-V2-bf16

from Jackrong/Qwopus3.8-27B-Flash-V2
bf16
Vision + text · Jackrong ↓ 152 · ♥ 0
Params
27B
Weights
≈ 54.7 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-09-22

dots.mocr-4bit

from dots-studio/dots.mocr
4-bit
Vision + text · dots-studio ↓ 152 · ♥ 0
Params
3.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+

mit · updated 2026-04-03

LocateAnything-3B-4bit

from nvidia/LocateAnything-3B
4-bit
Vision + text · NVIDIA ↓ 151 · ♥ 20
Params
3.5B
Weights
≈ 2.6 GB
Mac memory
8 GB+

nvidia-license · updated 2026-05-29

Qwen3-4B-4bit-DWQ-053125

from Qwen/Qwen3-4B
4-bit DWQ
Text generation · Qwen ↓ 151 · ♥ 2
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-01

DeepSeek-OCR-2-6bit

mlx-community/DeepSeek-OCR-2-6bit
6-bit
Vision + text ↓ 151 · ♥ 1
Params
3.4B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-28

DeepSeek-R1-Distill-Qwen-32B-Japanese

from cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese
Text generation · cyberagent ↓ 151 · ♥ 1
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

mit · updated 2025-01-27

starcoder2-3b-4bit

mlx-community/starcoder2-3b-4bit
4-bit
Text generation ↓ 151 · ♥ 1
Params
3.0B
Weights
≈ 1.9 GB
Mac memory
8 GB+

bigcode-openrail-m · updated 2024-03-01

NVIDIA-Nemotron-3-Super-120B-A12B-8bit

from nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
8-bit
Text generation · NVIDIA ↓ 151 · ♥ 0
Params
121B
Weights
≈ 128 GB
Mac memory
192 GB+

nvidia-nemotron-open-model-license · updated 2026-03-31

Qwen2.5-Coder-3B-8bit

from Qwen/Qwen2.5-Coder-3B
8-bit
Text generation · Qwen ↓ 151 · ♥ 0
Params
3.1B
Weights
≈ 3.3 GB
Mac memory
8 GB+

qwen-research · updated 2024-11-11

NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-MXFP4

from nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
MXFP4
Text generation · NVIDIA ↓ 150 · ♥ 3
Params
4.9B
Weights
≈ 2.8 GB
Mac memory
8 GB+

nvidia-open-model-license · updated 2025-12-17

Kimi-Dev-72B-8bit

from moonshotai/Kimi-Dev-72B
8-bit
Text generation · Moonshot · Kimi ↓ 150 · ♥ 2
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+

mit · updated 2025-07-12

Qwen2.5-14B-Instruct-8bit

from Qwen/Qwen2.5-14B
8-bit
Text generation · Qwen ↓ 150 · ♥ 2
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-09-18

Florence-2-base-ft-4bit

mlx-community/Florence-2-base-ft-4bit
4-bit
Vision + text ↓ 150 · ♥ 1
Params
271M
Weights
≈ 163 MB
Mac memory
8 GB+

mit · updated 2024-11-21

Hermes-3-Llama-3.2-3B-8bit

from NousResearch/Hermes-3-Llama-3.2-3B
8-bit
Text generation · NousResearch ↓ 150 · ♥ 1
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+

llama3 · updated 2024-12-11

deepseek-vl2-tiny-4bit

mlx-community/deepseek-vl2-tiny-4bit
4-bit
Vision + text ↓ 150 · ♥ 1
Params
3.4B
Weights
≈ 2.1 GB
Mac memory
8 GB+

deepseek · updated 2024-12-22

whisper-tiny-mlx-4bit

mlx-community/whisper-tiny-mlx-4bit
4-bit
Uncategorised ↓ 150 · ♥ 1
Params
23M
Weights
≈ 44 MB
Mac memory
8 GB+

updated 2024-01-28

AMD-Llama-135m-4bit

from amd/AMD-Llama-135m
4-bit
Uncategorised · amd ↓ 150 · ♥ 0
Params
134M
Weights
≈ 75 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-10-03

Kestrel-4B-Coder-4bit

from unsloth/Qwen3.5-4B
4-bit
Vision + text · unsloth ↓ 150 · ♥ 0
Params
4.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-07

Kimi-VL-A3B-Thinking-2506-5bit

from moonshotai/Kimi-VL-A3B-Instruct
5-bit
Vision + text · Moonshot · Kimi ↓ 150 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2026-01-27

Qwen2.5-3B-Instruct-8bit

from Qwen/Qwen2.5-3B
8-bit
Text generation · Qwen ↓ 150 · ♥ 0
Params
3.1B
Weights
≈ 3.3 GB
Mac memory
8 GB+

qwen-research · updated 2024-09-18

Laguna-S-2.1-oQ2e

from poolside/Laguna-S-2.1
2-bit
Text generation · poolside ↓ 149 · ♥ 12
Params
118B
Weights
≈ 36.8 GB
Mac memory
48 GB+

openmdw-1.1 · updated 2026-07-24

Hy3-OptiQ-2bit

from tencent/Hy3
2-bit
Text generation · tencent ↓ 149 · ♥ 6
Params
295B
Weights
≈ 92.3 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-09-15

gemma-4-12b-coder-fable5-composer2.5

from yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1
Text generation · yuxinlu1 ↓ 149 · ♥ 5
Params
12B
Weights
≈ 23.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-06-21

whisper-large-mlx

mlx-community/whisper-large-mlx
Uncategorised ↓ 149 · ♥ 3
Params
—
Weights
—
Mac memory
—

updated 2024-03-09

ACE-Step-1.5-text-encoder-bf16

from Qwen/Qwen3-Embedding-0.6B
bf16
Text to audio · Qwen ↓ 149 · ♥ 0
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-28

MiMo-V2.5-ASR-MLX-4bit

from XiaomiMiMo/MiMo-V2.5-ASR
4-bit
Speech recognition · XiaomiMiMo ↓ 149 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-30

Qwen2.5-7B-Instruct-1M-abliterated-4bit

from huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
4-bit
Text generation · huihui-ai ↓ 149 · ♥ 0
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-19

Qwen3-VL-Reranker-2B-8bit

from Qwen/Qwen3-VL-2B-Instruct
8-bit
Reranking · Qwen ↓ 149 · ♥ 0
Params
2.1B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-14

maya1-4bit

mlx-community/maya1-4bit
4-bit
Text to speech ↓ 148 · ♥ 2
Params
3.3B
Weights
≈ 1.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-24

Kimi-VL-A3B-Thinking-2506-bf16

from moonshotai/Kimi-VL-A3B-Instruct
bf16
Vision + text · Moonshot · Kimi ↓ 148 · ♥ 1
Params
16B
Weights
≈ 32.8 GB
Mac memory
48 GB+

mit · updated 2026-01-27

Qwen3-235B-A22B-Instruct-2507-5bit

from Qwen/Qwen3-235B-A22B-Instruct-2507
5-bit
Text generation · Qwen ↓ 148 · ♥ 1
Params
235B
Weights
≈ 162 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-07-22

K2-Horizon-7B-8bit

from IFM/K2-Horizon-7B
8-bit
Text generation · IFM ↓ 148 · ♥ 0
Params
9.0B
Weights
≈ 9.6 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-30

sam3-bf16

from facebook/sam3
bf16
Uncategorised · facebook ↓ 147 · ♥ 6
Params
860M
Weights
≈ 1.7 GB
Mac memory
8 GB+

updated 2026-03-28

Kokoro-82M-6bit

from yl4579/StyleTTS2-LJSpeech
6-bit
Text to speech · yl4579 ↓ 147 · ♥ 3
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-01-05

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

from Orion-zhen/DeepSeek-R1-Distill-Qwen-7B-abliterated
4-bit
Uncategorised · Orion-zhen ↓ 147 · ♥ 2
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

gpl-3.0 · updated 2025-01-29

Ornith-1.0-35B-OptiQ-4bit-REAP-19B

from mlx-community/Ornith-1.0-35B-OptiQ-4bit
4-bit
Text generation ↓ 147 · ♥ 2
Params
19B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-15

Kimi-VL-A3B-Thinking-6bit

from OpenGVLab/InternVL3-1B-Instruct
6-bit
Vision + text · OpenGVLab ↓ 147 · ♥ 1
Params
—
Weights
—
Mac memory
—

qwen · updated 2026-01-27

plamo-2-translate-bf16

from pfnet/plamo-2-translate
bf16
Text generation · pfnet ↓ 147 · ♥ 1
Params
9.5B
Weights
≈ 19.1 GB
Mac memory
24 GB+

plamo-community-license · updated 2026-10-07

MiniCPM5-2B-bf16

from openbmb/MiniCPM5-2B
bf16
Text generation · openbmb ↓ 147 · ♥ 0
Params
2.5B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-10

aya-expanse-8b-4bit

from CohereLabs/aya-expanse-8b
4-bit
Text generation · Cohere ↓ 147 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2024-10-24

gemma-3-1b-it-8bit

from google/gemma-3-1b-it
8-bit
Text generation · Google · Gemma ↓ 146 · ♥ 5
Params
1.3B
Weights
≈ 1.4 GB
Mac memory
8 GB+

gemma · updated 2025-03-12

granite-4.1-3b-mxfp4

from ibm-granite/granite-4.1-3b
MXFP4
Text generation · IBM · Granite ↓ 146 · ♥ 5
Params
3.4B
Weights
≈ 1.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-30

Devstral-2-123B-Instruct-2512-8bit

from mistralai/Devstral-2-123B-Instruct-2512
8-bit
Text generation · Mistral ↓ 146 · ♥ 1
Params
125B
Weights
≈ 133 GB
Mac memory
192 GB+

other · updated 2025-12-10

pixtral-12b-8bit

mlx-community/pixtral-12b-8bit
8-bit
Vision + text ↓ 145 · ♥ 8
Params
13B
Weights
≈ 13.5 GB
Mac memory
24 GB+

updated 2024-09-30

medgemma-4b-it-4bit

from google/medgemma-4b-pt
4-bit
Vision + text · Google · Gemma ↓ 145 · ♥ 3
Params
5.0B
Weights
≈ 3.0 GB
Mac memory
8 GB+

health-ai-developer-foundations · updated 2025-06-09

Midnight-Miqu-70B-v1.5-MLX-8Bit

from sophosympatheia/Midnight-Miqu-70B-v1.5
8-bit
Text generation · sophosympatheia ↓ 145 · ♥ 2
Params
69B
Weights
≈ 73.3 GB
Mac memory
96 GB+

other · updated 2025-01-22

Qwen2.5-1.5B-Instruct-8bit

from Qwen/Qwen2.5-1.5B
8-bit
Text generation · Qwen ↓ 145 · ♥ 2
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Ministral-3-14B-Instruct-2512

from mistralai/Ministral-3-14B-Instruct-2512
Text generation · Mistral ↓ 145 · ♥ 1
Params
14B
Weights
≈ 27.0 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-12-03

gpt-oss-20b-Ja-Fin-Thinking-MLX-8bit

from nri-ai/gpt-oss-20b-Ja-Fin-Thinking
8-bit
Text generation · nri-ai ↓ 145 · ♥ 1
Params
21B
Weights
≈ 22.2 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-03-27