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 4m ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

2,922 builds · page 18 of 49 · clear filters

granite-4.0-tiny-preview-4bit

from ibm-granite/granite-4.0-tiny-preview
4-bit
Text generation · IBM · Granite ↓ 90 · ♥ 0
Params
6.7B
Weights
≈ 3.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-09-10

Qwen3-235B-A22B-Instruct-2507-3bit-DWQ

from mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit
3-bit DWQ
Text generation ↓ 89 · ♥ 6
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+

apache-2.0 · updated 2025-07-26

TinyMistral-248M-4bits

mlx-community/TinyMistral-248M-4bits
4-bit
Text generation ↓ 89 · ♥ 1
Params
248M
Weights
≈ 140 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-06-28

GLM-Z1-9B-0414-abliterated-4bit

from huihui-ai/GLM-Z1-9B-0414-abliterated
4-bit
Text generation · huihui-ai ↓ 89 · ♥ 0
Params
9.4B
Weights
≈ 5.3 GB
Mac memory
8 GB+

mit · updated 2025-04-26

Josiefied-Qwen2.5-3B-Instruct-abliterated-v1-8-bit

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-3B-Instruct-abliterated-v1
8-bit
Text generation · Goekdeniz-Guelmez ↓ 89 · ♥ 0
Params
3.1B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-20

granite-3.3-2b-instruct-8bit

from ibm-granite/granite-3.3-2b-instruct
8-bit
Text generation · IBM · Granite ↓ 89 · ♥ 0
Params
2.5B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-16

Qwen2.5-14B-Instruct-bf16

from Qwen/Qwen2.5-14B
bf16
Text generation · Qwen ↓ 88 · ♥ 2
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-09-18

Mistral-Small-24B-Instruct-2501-writer

from lars1234/Mistral-Small-24B-Instruct-2501-writer
6-bit
Text generation · lars1234 ↓ 88 · ♥ 1
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-23

Step-3.5-Flash-6bit

from stepfun-ai/Step-3.5-Flash
6-bit
Text generation · stepfun-ai ↓ 88 · ♥ 1
Params
197B
Weights
≈ 160 GB
Mac memory
192 GB+

apache-2.0 · updated 2026-02-04

K2-Horizon-0.9B-4bit

from IFM/K2-Horizon-0.9B
4-bit
Text generation · IFM ↓ 88 · ♥ 0
Params
1.1B
Weights
≈ 607 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-30

Qwen3-1.7B-3bit

from Qwen/Qwen3-1.7B
3-bit
Text generation · Qwen ↓ 88 · ♥ 0
Params
1.7B
Weights
≈ 753 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

sarashina2.2-3b-instruct-v0.1-8bit

from sbintuitions/sarashina2.2-3b-instruct-v0.1
8-bit
Text generation · sbintuitions ↓ 88 · ♥ 0
Params
3.4B
Weights
≈ 3.6 GB
Mac memory
8 GB+

mit · updated 2025-03-05

tiny-aya-fire

from CohereLabs/tiny-aya-fire
Text generation · Cohere ↓ 88 · ♥ 0
Params
3.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+

cc-by-nc-4.0 · updated 2026-03-05

DeepSeek-R1-0528-Qwen3-8B-bf16

from deepseek-ai/deepseek-r1-0528-Qwen3-8B
bf16
Text generation · DeepSeek ↓ 87 · ♥ 4
Params
8.2B
Weights
≈ 16.4 GB
Mac memory
24 GB+

mit · updated 2025-05-29

Falcon-H1-3B-Instruct-4bit

from tiiuae/Falcon-H1-3B-Instruct
4-bit
Text generation · TII · Falcon ↓ 87 · ♥ 0
Params
3.1B
Weights
≈ 1.8 GB
Mac memory
8 GB+

falcon-llm-license · updated 2025-06-16

WhiteRabbitNeo-2.5-Qwen-2.5-Coder-12.3B

from win10/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-12.3B
4-bit
Text generation · win10 ↓ 87 · ♥ 0
Params
12B
Weights
≈ 6.9 GB
Mac memory
16 GB+

updated 2025-03-01

gemma-4-12B-it-qat-assistant-bf16

from google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
bf16
Text generation · Google · Gemma ↓ 87 · ♥ 0
Params
423M
Weights
≈ 846 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

magnum-v3-34b-4bit

from anthracite-org/magnum-v3-34b
4-bit
Text generation · anthracite-org ↓ 87 · ♥ 0
Params
34B
Weights
≈ 19.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-12-14

Ornith-1.0-9B-6bit

from ornith-ai/Ornith-1.0-9B
6-bit
Text generation · ornith-ai ↓ 86 · ♥ 6
Params
9.4B
Weights
≈ 8.2 GB
Mac memory
16 GB+

mit · updated 2026-06-28

Qwen3-32B-6bit

from Qwen/Qwen3-32B
6-bit
Text generation · Qwen ↓ 86 · ♥ 1
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-04-28

Hermes-4-14B-6bit

from NousResearch/Hermes-4-14B
6-bit
Text generation · NousResearch ↓ 86 · ♥ 0
Params
15B
Weights
≈ 12.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-09-03

Mistral-Small-24B-Instruct-2501-abliterated

from huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
Text generation · huihui-ai ↓ 86 · ♥ 0
Params
24B
Weights
≈ 47.1 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-02-20

Qwen2.5-Coder-0.5B-bf16

from Qwen/Qwen2.5-Coder-0.5B
bf16
Text generation · Qwen ↓ 86 · ♥ 0
Params
494M
Weights
≈ 988 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-11

bigcode-starcoder2-15b-fp16

from bigcode/starcoder2-15b
fp16
Text generation · BigCode ↓ 86 · ♥ 0
Params
16B
Weights
≈ 31.9 GB
Mac memory
48 GB+

bigcode-openrail-m · updated 2025-02-16

gemma-3-1b-it-abliterated-8bit

from mlabonne/gemma-3-1b-it-abliterated
8-bit
Text generation · mlabonne ↓ 86 · ♥ 0
Params
1.3B
Weights
≈ 1.4 GB
Mac memory
8 GB+

gemma · updated 2025-03-22

LFM2-8B-A1B-3bit-MLX

from LiquidAI/LFM2-8B-A1B
3-bit
Text generation · LiquidAI ↓ 85 · ♥ 2
Params
8.3B
Weights
≈ 3.6 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-10-08

aya-23-8B-4bit

mlx-community/aya-23-8B-4bit
4-bit
Text generation ↓ 85 · ♥ 2
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2024-05-23

Devstral-Small-2507-5bit

from mlx-community/Devstral-Samll-2507-bf16
5-bit
Text generation ↓ 85 · ♥ 1
Params
24B
Weights
≈ 16.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-11

Phi-4-mini-reasoning-8bit

from microsoft/Phi-4-mini-reasoning
8-bit
Text generation · Microsoft · Phi ↓ 85 · ♥ 0
Params
3.8B
Weights
≈ 4.1 GB
Mac memory
8 GB+

mit · updated 2025-05-01

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

from huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
6-bit
Text generation · huihui-ai ↓ 85 · ♥ 0
Params
7.6B
Weights
≈ 6.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-02-19

gemma-2-27b-it-bf16-4bit

from google/gemma-2-27b-it
4-bit
Text generation · Google · Gemma ↓ 85 · ♥ 0
Params
27B
Weights
≈ 15.3 GB
Mac memory
24 GB+

gemma · updated 2024-11-06

XYZ-Aquila-mini-OptiQ-4bit

from XYZAILab/XYZ-Aquila-mini
4-bit
Text generation · XYZAILab ↓ 84 · ♥ 4
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-09-15

Qwen2-Math-72B-Instruct-8bit

mlx-community/Qwen2-Math-72B-Instruct-8bit
8-bit
Text generation ↓ 84 · ♥ 2
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+

tongyi-qianwen · updated 2024-08-10

Trinity-Mini-4bit

from arcee-ai/Trinity-Mini
4-bit
Text generation · arcee-ai ↓ 84 · ♥ 1
Params
26B
Weights
≈ 14.7 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-12-02

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

mlx-community/Meta-Llama-3.1-8B-Instruct-abliterated-8bit
8-bit
Text generation ↓ 84 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.1 · updated 2024-08-03

Qwen2.5-7B-Instruct-kowiki-qa

mlx-community/Qwen2.5-7B-Instruct-kowiki-qa
Text generation ↓ 84 · ♥ 0
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-12-20

granite-3b-code-instruct-4bit

from ibm-granite/granite-3b-code-base-2k
4-bit
Text generation · IBM · Granite ↓ 84 · ♥ 0
Params
3.5B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-05-06

llm-jp-3.1-1.8b-instruct4-4bit

from llm-jp/llm-jp-3.1-1.8b-instruct4
4-bit
Text generation · llm-jp ↓ 84 · ♥ 0
Params
1.9B
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-22

phi-2-dpo-7k

mlx-community/phi-2-dpo-7k
Text generation ↓ 83 · ♥ 15
Params
—
Weights
—
Mac memory
—

mit · updated 2024-02-02

Laguna-S-2.1-oQ3e

from poolside/Laguna-S-2.1
3-bit
Text generation · poolside ↓ 83 · ♥ 4
Params
118B
Weights
≈ 51.5 GB
Mac memory
64 GB+

openmdw-1.1 · updated 2026-07-24

VibeThinker-3B

from WeiboAI/VibeThinker-3B
Text generation · WeiboAI ↓ 83 · ♥ 2
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

mit · updated 2026-06-21

Hy3-oQ2

from tencent/Hy3
2-bit
Text generation · tencent ↓ 82 · ♥ 9
Params
295B
Weights
≈ 92.3 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-07-15

Qwen3-Next-80B-A3B-Instruct-6bit

from Qwen/Qwen3-Next-80B-A3B-Instruct
6-bit
Text generation · Qwen ↓ 82 · ♥ 4
Params
80B
Weights
≈ 64.7 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-09-13

Hermes-4-70B-5bit

from NousResearch/Hermes-4-70B
5-bit
Text generation · NousResearch ↓ 82 · ♥ 2
Params
71B
Weights
≈ 48.5 GB
Mac memory
64 GB+

llama3 · updated 2025-08-26

Qwen3-1.7B-MLX-MXFP4

from Qwen/Qwen3-1.7B
MXFP4
Text generation · Qwen ↓ 82 · ♥ 2
Params
1.7B
Weights
≈ 968 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-24

Llama-3.1-Swallow-8B-Instruct-v0.1

from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1
Text generation · tokyotech-llm ↓ 82 · ♥ 1
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3.1 · updated 2024-10-08

llm-jp-3-13b-instruct

mlx-community/llm-jp-3-13b-instruct
Text generation ↓ 82 · ♥ 1
Params
14B
Weights
≈ 27.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-09-25

EXAONE-3.5-7.8B-Instruct-3bit

from LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct
3-bit
Text generation · LGAI-EXAONE ↓ 82 · ♥ 0
Params
7.8B
Weights
≈ 3.4 GB
Mac memory
8 GB+

exaone · updated 2024-12-23

Huihui-gemma-3n-E4B-it-abliterated-lm-4bit

from huihui-ai/Huihui-gemma-3n-E4B-it-abliterated
4-bit
Text generation · huihui-ai ↓ 82 · ♥ 0
Params
6.9B
Weights
≈ 3.9 GB
Mac memory
8 GB+

gemma · updated 2025-09-26

Qwen3-4B-6bit

from Qwen/Qwen3-4B
6-bit
Text generation · Qwen ↓ 82 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

Qwen3-4B-Instruct-2507-mxfp4

from Qwen/Qwen3-4B-Instruct-2507
MXFP4
Text generation · Qwen ↓ 82 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-08

gemma-3-4b-it-abliterated-6bit-text

from mlabonne/gemma-3-4b-it-abliterated
6-bit
Text generation · mlabonne ↓ 82 · ♥ 0
Params
4.6B
Weights
≈ 3.7 GB
Mac memory
8 GB+

gemma · updated 2025-03-22

tiny-aya-fire-4bit

from CohereLabs/tiny-aya-fire
4-bit
Text generation · Cohere ↓ 82 · ♥ 0
Params
3.3B
Weights
≈ 1.9 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2026-03-05

Phi-3-mini-128k-instruct-8bit

mlx-community/Phi-3-mini-128k-instruct-8bit
8-bit
Text generation ↓ 81 · ♥ 10
Params
3.8B
Weights
≈ 4.1 GB
Mac memory
8 GB+

mit · updated 2024-07-11

QwQ-32B-Preview-6bit

from Qwen/QwQ-32B-Preview
6-bit
Text generation · Qwen ↓ 81 · ♥ 4
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2024-11-27

YandexGPT-5-Lite-8B-instruct-q2

from yandex/YandexGPT-5-Lite-8B-instruct
2-bit
Text generation · yandex ↓ 81 · ♥ 2
Params
8.0B
Weights
≈ 2.5 GB
Mac memory
8 GB+

updated 2026-03-19

Qwen2-0.5B-Instruct-4bit

mlx-community/Qwen2-0.5B-Instruct-4bit
4-bit
Text generation ↓ 81 · ♥ 1
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-06-06