Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,842 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

5,842 builds · page 48 of 98

whisper-base-mlx-8bit

mlx-community/whisper-base-mlx-8bit
8-bit
Uncategorised ↓ 58 · ♥ 1
Params
—
Weights
—
Mac memory
—

updated 2024-03-09

Baichuan-M1-14B-Instruct

from baichuan-inc/Baichuan-M1-14B-Instruct
Text generation · baichuan-inc ↓ 58 · ♥ 0
Params
14B
Weights
≈ 28.9 GB
Mac memory
48 GB+

updated 2025-04-24

Bio-Medical-3B-CoT-012025

from ContactDoctor/Bio-Medical-3B-CoT-012025
4-bit
Text generation · ContactDoctor ↓ 58 · ♥ 0
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

other · updated 2025-01-26

LFM2.5-VL-450M-8bit

from LiquidAI/LFM2.5-VL-450M
8-bit
Vision + text · LiquidAI ↓ 58 · ♥ 0
Params
449M
Weights
≈ 557 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

Meta-Llama-Guard-2-8B-4bit

mlx-community/Meta-Llama-Guard-2-8B-4bit
4-bit
Text generation ↓ 58 · ♥ 0
Params
8.0B
Weights
≈ 5.3 GB
Mac memory
8 GB+

llama3 · updated 2024-04-19

Molmo-7B-D-0924-6bit

from Qwen/Qwen2-7B
6-bit
Vision + text · Qwen ↓ 58 · ♥ 0
Params
8.0B
Weights
≈ 7.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-12-27

Qwen3-VL-4B-Instruct-5bit

mlx-community/Qwen3-VL-4B-Instruct-5bit
5-bit
Vision + text ↓ 58 · ♥ 0
Params
4.4B
Weights
≈ 3.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

Qwen3-VL-4B-Instruct-6bit

mlx-community/Qwen3-VL-4B-Instruct-6bit
6-bit
Vision + text ↓ 58 · ♥ 0
Params
4.4B
Weights
≈ 4.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

UI-Venus-1.5-2B-bf16

from inclusionAI/UI-Venus-1.5-2B
bf16
Vision + text · inclusionAI ↓ 58 · ♥ 0
Params
2.4B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-20

Unsloth-Phi-4-mini-instruct-4bit

from unsloth/Phi-4-mini-instruct
4-bit
Text generation · unsloth ↓ 58 · ♥ 0
Params
3.8B
Weights
≈ 2.2 GB
Mac memory
8 GB+

mit · updated 2025-05-29

Video-Depth-Anything-Large-MLX

mlx-community/Video-Depth-Anything-Large-MLX
Depth estimation ↓ 58 · ♥ 0
Params
385M
Weights
≈ 1.5 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2026-09-01

VulnLLM-R-7B-6bit

from Virtue-AI-HUB/VulnLLM-R-7B
6-bit
Text generation · Virtue-AI-HUB ↓ 58 · ♥ 0
Params
7.6B
Weights
≈ 6.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-01-02

c4ai-command-r7b-12-2024-6bit

from CohereLabs/c4ai-command-r7b-12-2024
6-bit
Text generation · Cohere ↓ 58 · ♥ 0
Params
8.0B
Weights
≈ 6.5 GB
Mac memory
16 GB+

cc-by-nc-4.0 · updated 2024-12-16

QwQ-32B-Preview-8bit

from Qwen/QwQ-32B-Preview
8-bit
Text generation · Qwen ↓ 57 · ♥ 6
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-11-27

Jan-v3-4B-base-instruct-8bit

from janhq/Jan-v3-4B-base-instruct
8-bit
Text generation · janhq ↓ 57 · ♥ 3
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-27

MiniCPM-V-4.6-mxfp8

from openbmb/MiniCPM-V-4.6
MXFP8
Vision + text · openbmb ↓ 57 · ♥ 3
Params
1.3B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-13

Jan-nano-128k-4bit

from Menlo/Jan-nano-128k
4-bit
Text generation · Menlo ↓ 57 · ♥ 2
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-26

Meta-Llama-3.1-405B-2bit

mlx-community/Meta-Llama-3.1-405B-2bit
2-bit
Text generation ↓ 57 · ♥ 2
Params
410B
Weights
≈ 128 GB
Mac memory
192 GB+

llama3.1 · updated 2024-07-24

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

mlx-community/Phi-3-medium-128k-instruct-8bit
8-bit
Text generation ↓ 57 · ♥ 2
Params
14B
Weights
≈ 14.8 GB
Mac memory
24 GB+

mit · updated 2024-07-11

SeedVR2-3B-mlx

mlx-community/SeedVR2-3B-mlx
Image to image ↓ 57 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-06-06

granite-4.0-h-tiny-3bit-MLX

from ibm-granite/granite-4.0-h-tiny
3-bit
Text generation · IBM · Granite ↓ 57 · ♥ 2
Params
6.9B
Weights
≈ 3.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-03

AnimeGen-T2V-A14B-Lightning-int4

from Wan-AI/Wan2.2-T2V-A14B
Text to video · Wan-AI ↓ 57 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-07-14

Hy-MT2-1.8B-bf16

from Tencent-Hunyuan/Hy-MT2-1.8B
bf16
Translation · Tencent-Hunyuan ↓ 57 · ♥ 1
Params
1.8B
Weights
≈ 3.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-31

Qwen2.5-72B-Instruct-4bit-AWQ

from Qwen/Qwen2.5-72B-Instruct
4-bit
Text generation · Qwen ↓ 57 · ♥ 1
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+

qwen · updated 2025-04-26

Qwen3-4B-Instruct-2507-gabliterated-8bit

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
8-bit
Text generation · Goekdeniz-Guelmez ↓ 57 · ♥ 1
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2026-01-06

Qwopus3.6-27B-Coder-4bit

from Jackrong/Qwopus3.6-27B-Coder
4-bit
Vision + text · Jackrong ↓ 57 · ♥ 1
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-01

AceReason-Nemotron-14B-4bit

from nvidia/AceReason-Nemotron-14B
4-bit
Text generation · NVIDIA ↓ 57 · ♥ 0
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

nvidia-open-model-license · updated 2025-05-24

Dolphin3.0-Llama3.1-8B-bf16

from dphn/Dolphin3.0-Llama3.1-8B
bf16
Uncategorised · dphn ↓ 57 · ♥ 0
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3.1 · updated 2025-01-05

Falcon3-Mamba-7B-Instruct-8bits

from tiiuae/Falcon3-Mamba-7B-Instruct
8-bit
Text generation · TII · Falcon ↓ 57 · ♥ 0
Params
7.3B
Weights
≈ 7.7 GB
Mac memory
16 GB+

falcon-llm-license · updated 2025-02-14

GLM-4.5-Air-nvfp4

from zai-org/GLM-4.5-Air
4-bit
Text generation · zai-org ↓ 57 · ♥ 0
Params
107B
Weights
≈ 60.1 GB
Mac memory
96 GB+

mit · updated 2026-05-06

GLM-4.6V-5bit

mlx-community/GLM-4.6V-5bit
5-bit
Vision + text ↓ 57 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-12-08

LFM2-350M-ENJP-MT-8bit

from LiquidAI/LFM2-350M-ENJP-MT
8-bit
Text generation · LiquidAI ↓ 57 · ♥ 0
Params
354M
Weights
≈ 377 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-09-05

LFM2.5-350M-6bit

from LiquidAI/LFM2.5-350M
6-bit
Text generation · LiquidAI ↓ 57 · ♥ 0
Params
354M
Weights
≈ 288 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

Llama-3-ELYZA-JP-8B-4bit

mlx-community/Llama-3-ELYZA-JP-8B-4bit
4-bit
Text generation ↓ 57 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3 · updated 2024-06-26

Mellum-4b-sft-python-4bit

from JetBrains/Mellum-4b-sft-python
4-bit
Text generation · JetBrains ↓ 57 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-28

Meta-Llama-3.1-8B-Instruct-abliterated-2bit

mlx-community/Meta-Llama-3.1-8B-Instruct-abliterated-2bit
2-bit
Text generation ↓ 57 · ♥ 0
Params
8.0B
Weights
≈ 2.5 GB
Mac memory
8 GB+

llama3.1 · updated 2024-08-03

Qwen2.5-32B-8bit

mlx-community/Qwen2.5-32B-8bit
8-bit
Text generation ↓ 57 · ♥ 0
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-09-18

Violet-Lyra-Gutenberg-4bit

from ohyeah1/Violet-Lyra-Gutenberg
4-bit
Text generation · ohyeah1 ↓ 57 · ♥ 0
Params
12B
Weights
≈ 6.9 GB
Mac memory
16 GB+

updated 2025-02-24

YOLO26n-OptiQ-6bit

from Ultralytics/YOLO26
6-bit
Object detection · Ultralytics ↓ 57 · ♥ 0
Params
—
Weights
—
Mac memory
—

agpl-3.0 · updated 2026-09-28

gemma-3-4b-it-qat-3bit

from google/gemma-3-4b-it
3-bit
Vision + text · Google · Gemma ↓ 57 · ♥ 0
Params
5.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+

gemma · updated 2025-04-18

gemma-4-12B-it-qat-assistant-mxfp4

from google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
MXFP4
Text generation · Google · Gemma ↓ 57 · ♥ 0
Params
423M
Weights
≈ 238 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

granite-20b-code-instruct-4bit

from ibm-granite/granite-20b-code-base-8k
4-bit
Text generation · IBM · Granite ↓ 57 · ♥ 0
Params
20B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-05-14

granite-4.0-3b-vision-8bit

from ibm-granite/granite-4.0-3b-vision
8-bit
Vision + text · IBM · Granite ↓ 57 · ♥ 0
Params
4.3B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-01

medgemma-27b-it-6bit

from google/gemma-3-27b-pt
6-bit
Vision + text · Google · Gemma ↓ 57 · ♥ 0
Params
—
Weights
—
Mac memory
—

health-ai-developer-foundations · updated 2025-07-10

whisper-large-v3-asr-8bit

mlx-community/whisper-large-v3-asr-8bit
8-bit
Uncategorised ↓ 57 · ♥ 0
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

updated 2026-01-13

ACE-Step-v1.5-turbo-bf16

mlx-community/ACE-Step-v1.5-turbo-bf16
bf16
Uncategorised ↓ 56 · ♥ 4
Params
2.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+

updated 2026-03-21

Hy3-oQ2e

from tencent/Hy3
2-bit
Text generation · tencent ↓ 56 · ♥ 4
Params
295B
Weights
≈ 92.3 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-07-15

DeepCoder-14B-Preview-8bit

from agentica-org/DeepCoder-14B-Preview
8-bit
Text generation · agentica-org ↓ 56 · ♥ 3
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+

mit · updated 2025-04-08

gemma-4-26b-a4b-6bit

from google/gemma-4-26b-a4b
6-bit
Vision + text · Google · Gemma ↓ 56 · ♥ 3
Params
26B
Weights
≈ 21.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-03

granite-3.3-8b-instruct-fp16

from ibm-granite/granite-3.3-8b-instruct
fp16
Text generation · IBM · Granite ↓ 56 · ♥ 3
Params
8.2B
Weights
≈ 16.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-04-16

paligemma2-10b-ft-docci-448-bf16

mlx-community/paligemma2-10b-ft-docci-448-bf16
bf16
Vision + text ↓ 56 · ♥ 3
Params
9.7B
Weights
≈ 19.3 GB
Mac memory
24 GB+

gemma · updated 2024-12-16

LFM2-1.2B-8bit

from LiquidAI/LFM2-1.2B
8-bit
Text generation · LiquidAI ↓ 56 · ♥ 2
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-07-12

Qwen3-30B-A3B-4bit-DWQ-10072025

from Qwen/Qwen3-30B-A3B
4-bit DWQ
Text generation · Qwen ↓ 56 · ♥ 2
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-10

ERNIE-4.5-0.3B-PT-4bit

from baidu/ERNIE-4.5-0.3B-PT
4-bit
Text generation · baidu ↓ 56 · ♥ 1
Params
361M
Weights
≈ 203 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-02

Josiefied-Qwen3-8B-abliterated-v1-6bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
6-bit
Text generation · Goekdeniz-Guelmez ↓ 56 · ♥ 1
Params
8.2B
Weights
≈ 6.7 GB
Mac memory
16 GB+

updated 2025-05-02

Meta-Llama-3.1-70B-8bit

mlx-community/Meta-Llama-3.1-70B-8bit
8-bit
Text generation ↓ 56 · ♥ 1
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3.1 · updated 2024-07-24

QwQ-32B-Coder-Fusion-9010-4bit

from huihui-ai/QwQ-32B-Coder-Fusion-9010
4-bit
Text generation · huihui-ai ↓ 56 · ♥ 1
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-12-11

Qwen3-VL-30B-A3B-Thinking-3bit

mlx-community/Qwen3-VL-30B-A3B-Thinking-3bit
3-bit
Vision + text ↓ 56 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14