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 2h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

2,922 builds · page 15 of 49 · clear filters

LFM2.5-8B-A1B-MLX-8bit

from LiquidAI/LFM2.5-8B-A1B
8-bit
Text generation · LiquidAI ↓ 118 · ♥ 6
Params
8.5B
Weights
≈ 9.0 GB
Mac memory
16 GB+

lfm1.0 · updated 2026-08-13

GLM-4.7-8bit

from zai-org/GLM-4.7
8-bit
Text generation · zai-org ↓ 118 · ♥ 3
Params
353B
Weights
≈ 375 GB
Mac memory
512 GB+

mit · updated 2026-02-18

gemma-4-12B-it-qat-assistant-8bit

from google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
8-bit
Text generation · Google · Gemma ↓ 118 · ♥ 0
Params
423M
Weights
≈ 449 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

lille-130m-instruct-bf16

from mlx-community/lille-130m-instruct-fp16
bf16
Text generation ↓ 118 · ♥ 0
Params
127M
Weights
≈ 254 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-09-05

VibeThinker-1.5B-mlx-4bit

from WeiboAI/VibeThinker-1.5B
4-bit
Text generation · WeiboAI ↓ 117 · ♥ 26
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+

mit · updated 2025-11-19

GLM-4.5-4bit

from zai-org/GLM-4.5
4-bit
Text generation · zai-org ↓ 117 · ♥ 16
Params
353B
Weights
≈ 199 GB
Mac memory
256 GB+

mit · updated 2025-07-28

Qwen3-0.6B-4bit-AWQ

from Qwen/Qwen3-0.6B
4-bit
Text generation · Qwen ↓ 117 · ♥ 3
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-05-03

Qwen2.5-14B-Instruct-3bit

from Qwen/Qwen2.5-14B
3-bit
Text generation · Qwen ↓ 117 · ♥ 2
Params
15B
Weights
≈ 6.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-04-28

Laguna-XS-2.1-6bit

from poolside/Laguna-XS-2.1
6-bit
Text generation · poolside ↓ 117 · ♥ 1
Params
33B
Weights
≈ 27.2 GB
Mac memory
48 GB+

openmdw-1.1 · updated 2026-07-03

K2-Horizon-0.9B-8bit

from IFM/K2-Horizon-0.9B
8-bit
Text generation · IFM ↓ 117 · ♥ 0
Params
1.1B
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-30

Llama-3.1-Swallow-70B-Instruct-v0.3-4bit

from tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
4-bit
Text generation · tokyotech-llm ↓ 117 · ♥ 0
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+

llama3.1 · updated 2025-03-10

DeepSeek-V2.5-1210-4bit

from deepseek-ai/DeepSeek-V2.5-1210
4-bit
Text generation · DeepSeek ↓ 116 · ♥ 4
Params
236B
Weights
≈ 133 GB
Mac memory
192 GB+

deepseek · updated 2024-12-11

ABEJA-Qwen2.5-32b-Japanese-v0.1

from abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1
Text generation · abeja ↓ 116 · ♥ 0
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-01-27

Qwen3-Coder-Next-nvfp4

from Qwen/Qwen3-Coder-Next
4-bit
Text generation · Qwen ↓ 116 · ♥ 0
Params
80B
Weights
≈ 44.8 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-05-06

TinySwallow-1.5B-Instruct-8bit

from SakanaAI/TinySwallow-1.5B-Instruct
8-bit
Text generation · SakanaAI ↓ 116 · ♥ 0
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-30

codegemma-7b-it-4bit

mlx-community/codegemma-7b-it-4bit
4-bit
Text generation ↓ 115 · ♥ 2
Params
8.5B
Weights
≈ 5.9 GB
Mac memory
16 GB+

gemma · updated 2024-04-09

Qwen2.5-3B-Instruct-bf16

from Qwen/Qwen2.5-3B
bf16
Text generation · Qwen ↓ 115 · ♥ 1
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

qwen-research · updated 2024-09-18

Qwen2.5-7B-Instruct-3bit

from Qwen/Qwen2.5-7B-Instruct
3-bit
Text generation · Qwen ↓ 115 · ♥ 0
Params
7.6B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-14

OpenHermes-2.5-Mistral-7B

mlx-community/OpenHermes-2.5-Mistral-7B
Text generation ↓ 114 · ♥ 6
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-02-10

Cydonia-24B-v3-4bit

from TheDrummer/Cydonia-24B-v3
4-bit
Text generation · TheDrummer ↓ 114 · ♥ 1
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+

other · updated 2025-06-04

GLM-4-9B-0414-8bit

from zai-org/GLM-4-9B-0414
8-bit
Text generation · zai-org ↓ 114 · ♥ 0
Params
9.4B
Weights
≈ 10.0 GB
Mac memory
16 GB+

mit · updated 2025-04-17

starcoder2-15b-4bit

mlx-community/starcoder2-15b-4bit
4-bit
Text generation ↓ 114 · ♥ 0
Params
7.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+

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

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

from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
4-bit
Text generation · DeepSeek ↓ 113 · ♥ 4
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

mit · updated 2025-06-29

Kimi-K2-Instruct-0905-mlx-3bit

from moonshotai/Kimi-K2-Instruct-0905
3-bit
Text generation · Moonshot · Kimi ↓ 113 · ♥ 3
Params
1.0T
Weights
≈ 449 GB
Mac memory
512 GB+

modified-mit · updated 2025-09-06

gemma-2-27b-it-bf16

mlx-community/gemma-2-27b-it-bf16
bf16
Text generation ↓ 113 · ♥ 2
Params
27B
Weights
≈ 54.5 GB
Mac memory
64 GB+

gemma · updated 2024-11-06

Hermes-4-70B-8bit

from NousResearch/Hermes-4-70B
8-bit
Text generation · NousResearch ↓ 113 · ♥ 1
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3 · updated 2025-08-26

llm-jp-3-7.2b-instruct3-4bit

from llm-jp/llm-jp-3-7.2b-instruct3
4-bit
Text generation · llm-jp ↓ 113 · ♥ 0
Params
7.3B
Weights
≈ 4.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-07

Yi-Coder-9B-Chat-4bit

mlx-community/Yi-Coder-9B-Chat-4bit
4-bit
Text generation ↓ 112 · ♥ 2
Params
8.8B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-05

Llama-2-7b-chat-4-bit

mlx-community/Llama-2-7b-chat-4-bit
4-bit
Text generation ↓ 111 · ♥ 6
Params
—
Weights
—
Mac memory
—

llama2 · updated 2023-12-24

gemma-3-text-27b-it-4bit

from mlx-community/gemma-3-27b-it-bf16
4-bit
Text generation ↓ 111 · ♥ 3
Params
28B
Weights
≈ 16.0 GB
Mac memory
24 GB+

gemma · updated 2025-03-18

Qwen2.5-14B-Instruct-1M-6bit

from Qwen/Qwen2.5-14B-Instruct-1M
6-bit
Text generation · Qwen ↓ 111 · ♥ 2
Params
15B
Weights
≈ 12.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-01-26

Huihui-Qwen3.5-27B-abliterated-6bit

from huihui-ai/Huihui-Qwen3.5-27B-abliterated
6-bit
Text generation · huihui-ai ↓ 111 · ♥ 1
Params
27B
Weights
≈ 21.9 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-03-04

Qwen2.5-3B-4bit

mlx-community/Qwen2.5-3B-4bit
4-bit
Text generation ↓ 111 · ♥ 0
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

qwen-research · updated 2024-09-18

Llama-2-7b-mlx

mlx-community/Llama-2-7b-mlx
Text generation ↓ 110 · ♥ 13
Params
—
Weights
—
Mac memory
—

llama2 · updated 2023-12-20

VibeThinker-3B-8bit

from WeiboAI/VibeThinker-3B
8-bit
Text generation · WeiboAI ↓ 110 · ♥ 4
Params
3.1B
Weights
≈ 3.3 GB
Mac memory
8 GB+

mit · updated 2026-06-16

YandexGPTQ6

from yandex/YandexGPT-5-Lite-8B-instruct
6-bit
Text generation · yandex ↓ 110 · ♥ 2
Params
8.0B
Weights
≈ 6.5 GB
Mac memory
16 GB+

yandexgpt-5-lite-8b · updated 2026-03-20

Devstral-Small-2507-8bit

from mlx-community/Devstral-Samll-2507-bf16
8-bit
Text generation ↓ 110 · ♥ 1
Params
24B
Weights
≈ 25.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-11

Kimi-Dev-72B-6bit

from moonshotai/Kimi-Dev-72B
6-bit
Text generation · Moonshot · Kimi ↓ 110 · ♥ 1
Params
73B
Weights
≈ 59.1 GB
Mac memory
96 GB+

mit · updated 2025-07-12

calme-3.2-instruct-78b-4bit

from MaziyarPanahi/calme-3.2-instruct-78b
4-bit
Text generation · MaziyarPanahi ↓ 110 · ♥ 1
Params
78B
Weights
≈ 43.9 GB
Mac memory
64 GB+

qwen · updated 2024-12-15

Qwen3Guard-Gen-0.6B-MLX

from Qwen/Qwen3Guard-Gen-0.6B
Text generation · Qwen ↓ 110 · ♥ 0
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-09-30

Laguna-XS-2.1-3bit

from poolside/Laguna-XS-2.1
3-bit
Text generation · poolside ↓ 109 · ♥ 3
Params
33B
Weights
≈ 14.6 GB
Mac memory
24 GB+

openmdw-1.1 · updated 2026-07-03

MiniMax-M2.5-4bit

from MiniMaxAI/MiniMax-M2.5
4-bit
Text generation · MiniMaxAI ↓ 109 · ♥ 3
Params
229B
Weights
≈ 129 GB
Mac memory
192 GB+

modified-mit · updated 2026-02-13

DeepSeek-V4-Flash-6bit

mlx-community/DeepSeek-V4-Flash-6bit
6-bit
Text generation ↓ 109 · ♥ 2
Params
284B
Weights
≈ 231 GB
Mac memory
512 GB+

updated 2026-04-25

NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6Bit

from nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
6-bit
Text generation · NVIDIA ↓ 109 · ♥ 2
Params
6.9B
Weights
≈ 6.8 GB
Mac memory
16 GB+

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

Qwen2.5-7B-Instruct-1M-6bit

from Qwen/Qwen2.5-7B-Instruct-1M
6-bit
Text generation · Qwen ↓ 109 · ♥ 2
Params
7.6B
Weights
≈ 6.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-01-26

gemma-4-E2B-it-qat-assistant-bf16

from google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
bf16
Text generation · Google · Gemma ↓ 109 · ♥ 1
Params
78M
Weights
≈ 157 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

Qwen2.5-7B-Instruct-1M-3bit

from Qwen/Qwen2.5-7B-Instruct-1M
3-bit
Text generation · Qwen ↓ 109 · ♥ 0
Params
7.6B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-26

Qwen2.5-Coder-0.5B-4bit

from Qwen/Qwen2.5-Coder-0.5B
4-bit
Text generation · Qwen ↓ 109 · ♥ 0
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-11

Devstral-2-123B-Instruct-2512-6bit

from mistralai/Devstral-2-123B-Instruct-2512
6-bit
Text generation · Mistral ↓ 108 · ♥ 0
Params
125B
Weights
≈ 102 GB
Mac memory
128 GB+

other · updated 2025-12-10

gemma-3-4b-it-abliterated-4bit-text

from mlabonne/gemma-3-4b-it-abliterated
4-bit
Text generation · mlabonne ↓ 108 · ♥ 0
Params
4.6B
Weights
≈ 2.6 GB
Mac memory
8 GB+

gemma · updated 2025-03-22

openchat-3.5-0106-4bit-mlx

from mistralai/Mistral-7B-v0.1
4-bit
Text generation · Mistral ↓ 108 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-01-16

starcoder2-15b-instruct-v0.1-4bit

from bigcode/starcoder2-15b
4-bit
Text generation · BigCode ↓ 108 · ♥ 0
Params
16B
Weights
≈ 9.0 GB
Mac memory
16 GB+

bigcode-openrail-m · updated 2024-04-29

Hunyuan-A13B-Instruct-4bit

from tencent/Hunyuan-A13B-Instruct
4-bit
Text generation · tencent ↓ 107 · ♥ 4
Params
80B
Weights
≈ 45.2 GB
Mac memory
64 GB+

tencent-hunyuan-a13b · updated 2025-07-04

Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1
Text generation · Goekdeniz-Guelmez ↓ 107 · ♥ 2
Params
494M
Weights
≈ 988 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-17