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 59m ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

5,842 builds · page 45 of 98

GLM-Z1-9B-0414-abliterated-6bit

from huihui-ai/GLM-Z1-9B-0414-abliterated
6-bit
Text generation · huihui-ai ↓ 64 · ♥ 0
Params
9.4B
Weights
≈ 7.6 GB
Mac memory
16 GB+

mit · updated 2025-04-26

GOT-OCR2_0-8bit

from stepfun-ai/GOT-OCR2_0
8-bit
Vision + text · stepfun-ai ↓ 64 · ♥ 0
Params
561M
Weights
≈ 686 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-14

Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-4bit

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1
4-bit
Text generation · Goekdeniz-Guelmez ↓ 64 · ♥ 0
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-17

Llama-3.2-11B-Vision-Surgical-CholecT50-bf16

mlx-community/Llama-3.2-11B-Vision-Surgical-CholecT50-bf16
bf16
Uncategorised ↓ 64 · ♥ 0
Params
11B
Weights
≈ 21.3 GB
Mac memory
32 GB+

nvidia-community-model-license · updated 2025-06-04

Ministral-3-3B-Base-2512-6bit

from mistralai/Ministral-3-3B-Base-2512
6-bit
Vision + text · Mistral ↓ 64 · ♥ 0
Params
3.8B
Weights
≈ 3.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-18

Qwen2.5-7B-Instruct-kowiki-qa-4bit

mlx-community/Qwen2.5-7B-Instruct-kowiki-qa-4bit
4-bit
Text generation ↓ 64 · ♥ 0
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-20

Qwen3-0.6B-Base-DQ5

from mlx-community/Qwen3-0.6B-Base-bf16
4-bit
Text generation ↓ 64 · ♥ 0
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-25

Qwen3-VL-Embedding-2B-6bit

from Qwen/Qwen3-VL-2B-Instruct
6-bit
Embeddings · Qwen ↓ 64 · ♥ 0
Params
2.1B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-13

gemma-2-27b-it-bf16-8bit

from google/gemma-2-27b-it
8-bit
Text generation · Google · Gemma ↓ 64 · ♥ 0
Params
27B
Weights
≈ 28.9 GB
Mac memory
48 GB+

gemma · updated 2024-11-06

SmolVLM-Instruct-8bit

from HuggingFaceTB/SmolVLM-Instruct
8-bit
Vision + text · Hugging Face ↓ 63 · ♥ 9
Params
2.2B
Weights
≈ 2.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-29

LFM2-8B-A1B-8bit-MLX

from LiquidAI/LFM2-8B-A1B
8-bit
Text generation · LiquidAI ↓ 63 · ♥ 7
Params
8.3B
Weights
≈ 8.9 GB
Mac memory
16 GB+

lfm1.0 · updated 2025-10-08

stablelm-2-zephyr-1_6b-4bit

mlx-community/stablelm-2-zephyr-1_6b-4bit
4-bit
Uncategorised ↓ 63 · ♥ 5
Params
1.6B
Weights
≈ 1.2 GB
Mac memory
8 GB+

other · updated 2024-03-05

MiniMax-M2.5-6bit

from MiniMaxAI/MiniMax-M2.5
6-bit
Text generation · MiniMaxAI ↓ 63 · ♥ 4
Params
229B
Weights
≈ 186 GB
Mac memory
256 GB+

modified-mit · updated 2026-02-13

Qwen2-VL-72B-Instruct-8bit

mlx-community/Qwen2-VL-72B-Instruct-8bit
8-bit
Vision + text ↓ 63 · ♥ 4
Params
73B
Weights
≈ 78.0 GB
Mac memory
96 GB+

tongyi-qianwen · updated 2025-03-24

Josiefied-Qwen3-4B-abliterated-v1-6bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1
6-bit
Text generation · Goekdeniz-Guelmez ↓ 63 · ♥ 2
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

updated 2025-05-01

MiniMax-Music3-nvfp4

from MiniMaxAI/MiniMax-Music3
4-bit
Text to audio · MiniMaxAI ↓ 63 · ♥ 2
Params
12B
Weights
≈ 9.2 GB
Mac memory
16 GB+

minimax-music3-community-license · updated 2026-08-16

DeepSeek-OCR-5bit

mlx-community/DeepSeek-OCR-5bit
5-bit
Vision + text ↓ 63 · ♥ 1
Params
3.3B
Weights
≈ 2.8 GB
Mac memory
8 GB+

mit · updated 2026-01-28

Devstral-Samll-2507-bf16

from mistralai/Devstral-Small-2507
bf16
Text generation · Mistral ↓ 63 · ♥ 1
Params
24B
Weights
≈ 47.1 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-07-10

Qwen2-1.5B-Instruct-4bit

mlx-community/Qwen2-1.5B-Instruct-4bit
4-bit
Text generation ↓ 63 · ♥ 1
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-06-06

Seed-Coder-8B-Reasoning-6bit

from ByteDance-Seed/Seed-Coder-8B-Reasoning
6-bit
Text generation · ByteDance-Seed ↓ 63 · ♥ 1
Params
8.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+

mit · updated 2025-05-20

granite-vision-3.2-2b-nvfp4

from ibm-granite/granite-vision-3.2-2b
4-bit
Vision + text · IBM · Granite ↓ 63 · ♥ 1
Params
3.1B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-01

whisper-tiny-khmer-mlx-fp32

from openai-whisper-tiny
fp32
Speech recognition ↓ 63 · ♥ 1
Params
37M
Weights
≈ 149 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-25

3b-zh-pretrain-research_release-bf16

from meta-llama/Llama-3.2-3B-Instruct
bf16
Text to speech · Meta · Llama ↓ 63 · ♥ 0
Params
—
Weights
—
Mac memory
—

llama3.2 · updated 2025-04-10

GLM-4-9B-0414-bf16

from zai-org/GLM-4-9B-0414
bf16
Text generation · zai-org ↓ 63 · ♥ 0
Params
9.4B
Weights
≈ 18.8 GB
Mac memory
24 GB+

mit · updated 2025-04-17

GLM-4.6V-Flash-5bit

mlx-community/GLM-4.6V-Flash-5bit
5-bit
Vision + text ↓ 63 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-12-08

Hermes-4-14B-5bit

from NousResearch/Hermes-4-14B
5-bit
Text generation · NousResearch ↓ 63 · ♥ 0
Params
15B
Weights
≈ 10.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-09-03

InternVL3-8B-MLX-4bit

from mlx-community/InternVL3-8B-bf16
4-bit
Vision + text ↓ 63 · ♥ 0
Params
7.9B
Weights
≈ 4.9 GB
Mac memory
8 GB+

qwen · updated 2026-02-23

Mellum2-12B-A2.5B-Instruct-6bit

from JetBrains/Mellum2-12B-A2.5B-Instruct
6-bit
Text generation · JetBrains ↓ 63 · ♥ 0
Params
12B
Weights
≈ 9.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-08-11

Qwen2.5-Coder-0.5B-4bit-gs32

from Qwen/Qwen2.5-Coder-0.5B
4-bit
Text generation · Qwen ↓ 63 · ♥ 0
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-13

Qwen3-0.6B-Base-8bit

from Qwen/Qwen3-0.6B-Base
8-bit
Text generation · Qwen ↓ 63 · ♥ 0
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-25

RAI-3.0-R1-VECTOR-MLX-4bit

from Local-Novel-LLM-project/RAI-3.0-R1-VECTOR
4-bit
Text generation · Local-Novel-LLM-project ↓ 63 · ♥ 0
Params
671B
Weights
≈ 378 GB
Mac memory
512 GB+

apache-2.0 · updated 2026-05-01

SmolLM2-360M-Instruct-bf16-mlx

from HuggingFaceTB/SmolLM2-360M-Instruct
bf16
Text generation · Hugging Face ↓ 63 · ♥ 0
Params
362M
Weights
≈ 724 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-25

SoulX-Singer-8bit

from Soul-AILab/SoulX-Singer
8-bit
Text to audio · Soul-AILab ↓ 63 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-05-31

medgemma-27b-text-it-6bit

from google/medgemma-27b-text-it
6-bit
Text generation · Google · Gemma ↓ 63 · ♥ 0
Params
28B
Weights
≈ 23.1 GB
Mac memory
32 GB+

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

GLM-4.5-Air-2bit

from zai-org/GLM-4.5-Air
2-bit
Text generation · zai-org ↓ 62 · ♥ 4
Params
107B
Weights
≈ 33.4 GB
Mac memory
48 GB+

mit · updated 2025-07-28

Youtu-LLM-2B-4bit

from tencent/Youtu-LLM-2B
4-bit
Text generation · tencent ↓ 62 · ♥ 4
Params
2.2B
Weights
≈ 1.3 GB
Mac memory
8 GB+

tencent-youtu · updated 2026-01-01

LFM2-8B-A1B-6bit-MLX

from LiquidAI/LFM2-8B-A1B
6-bit
Text generation · LiquidAI ↓ 62 · ♥ 3
Params
8.3B
Weights
≈ 6.8 GB
Mac memory
16 GB+

lfm1.0 · updated 2025-10-08

gemma-4-31b-6bit

from google/gemma-4-31b
6-bit
Vision + text · Google · Gemma ↓ 62 · ♥ 3
Params
31B
Weights
≈ 26.1 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-02

Qwen2.5-14B-8bit

mlx-community/Qwen2.5-14B-8bit
8-bit
Text generation ↓ 62 · ♥ 2
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-09-18

SmolLM3-3B-bf16

from HuggingFaceTB/SmolLM3-3B
bf16
Text generation · Hugging Face ↓ 62 · ♥ 2
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-07-08

Falcon-H1-Tiny-Tool-Calling-90M-4bit

from tiiuae/Falcon-H1-Tiny-Tool-Calling-90M
4-bit
Text generation · TII · Falcon ↓ 62 · ♥ 1
Params
91M
Weights
≈ 51 MB
Mac memory
8 GB+

falcon-llm-license · updated 2026-01-28

GLM-OCR-6bit

mlx-community/GLM-OCR-6bit
6-bit
Image to text ↓ 62 · ♥ 1
Params
1.1B
Weights
≈ 1.4 GB
Mac memory
8 GB+

mit · updated 2026-02-03

Llama-3-Groq-70B-Tool-Use-8bit

mlx-community/Llama-3-Groq-70B-Tool-Use-8bit
8-bit
Text generation ↓ 62 · ♥ 1
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3 · updated 2024-07-17

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-bf16

from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
bf16
Vision + text · NVIDIA ↓ 62 · ♥ 1
Params
33B
Weights
≈ 66.0 GB
Mac memory
96 GB+

nvidia-open-model-agreement · updated 2026-04-29

North-Mini-Code-1.0-5bit

from CohereLabs/North-Mini-Code-1.0
5-bit
Vision + text · Cohere ↓ 62 · ♥ 1
Params
30B
Weights
≈ 22.2 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-06-10

Ring-1T-preview-3bit

from inclusionAI/Ring-1T-preview
3-bit
Text generation · inclusionAI ↓ 62 · ♥ 1
Params
1000B
Weights
≈ 437 GB
Mac memory
512 GB+

mit · updated 2025-09-29

Valkyrie-49B-v1-4bit

from TheDrummer/Valkyrie-49B-v1
4-bit
Uncategorised · TheDrummer ↓ 62 · ♥ 1
Params
50B
Weights
≈ 28.1 GB
Mac memory
48 GB+

updated 2025-05-27

meta-llama-Llama-4-Scout-17B-16E-6bit

from meta-llama/Llama-4-Scout-17B-16E
6-bit
Text generation · Meta · Llama ↓ 62 · ♥ 1
Params
108B
Weights
≈ 87.6 GB
Mac memory
128 GB+

llama4 · updated 2025-04-06

DeepSeek-R1-Distill-Llama-8B-6bit

from deepseek-ai/DeepSeek-R1-Distill-Llama-8B
6-bit
Uncategorised · DeepSeek ↓ 62 · ♥ 0
Params
8.0B
Weights
≈ 6.5 GB
Mac memory
16 GB+

updated 2025-02-26

InternVL3-38B-4bit

from OpenGVLab/InternVL3-1B-Instruct
4-bit
Vision + text · OpenGVLab ↓ 62 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-30

Josiefied-Hermes-3-Llama-3.2-3B-v1-8bit

from Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1
8-bit
Text generation · Goekdeniz-Guelmez ↓ 62 · ♥ 0
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+

updated 2025-10-28

Llama-3.1-Swallow-70B-Instruct-v0.1

from tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.1
Text generation · tokyotech-llm ↓ 62 · ♥ 0
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+

llama3.1 · updated 2024-10-08

Meta-Llama-3.1-8B-Instruct-4bit-fakenews

from meta-llama/Llama-3.1-8B-Instruct
4-bit
Text generation · Meta · Llama ↓ 62 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3.1 · updated 2024-11-07

MiniCPM4.1-8B-4bit

from openbmb/MiniCPM4.1-8B
4-bit
Text generation · openbmb ↓ 62 · ♥ 0
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-09-08

Qwen2.5-72B-Instruct-bf16

from Qwen/Qwen2.5-72B
bf16
Text generation · Qwen ↓ 62 · ♥ 0
Params
73B
Weights
≈ 145 GB
Mac memory
192 GB+

qwen · updated 2024-09-19

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

from Qwen/Qwen3-235B-A22B-Instruct-2507
3-bit
Text generation · Qwen ↓ 62 · ♥ 0
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+

apache-2.0 · updated 2025-07-22

Qwen3-4B-Thinking-2507-heretic-8bit

from Daizee/Qwen3-4B-Thinking-2507-heretic
8-bit
Text generation · Daizee ↓ 62 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-16

gemma-3-270m-4bit

from google/gemma-3-270m
4-bit
Text generation · Google · Gemma ↓ 62 · ♥ 0
Params
436M
Weights
≈ 245 MB
Mac memory
8 GB+

gemma · updated 2025-08-09