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

2,922 builds · page 27 of 49 · clear filters

ERNIE-4.5-21B-A3B-PT-8bit

from baidu/ERNIE-4.5-21B-A3B-PT
8-bit
Text generation · baidu ↓ 50 · ♥ 2
Params
22B
Weights
≈ 23.2 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-04

AI21-Jamba-Reasoning-3B-6bit

from ai21labs/AI21-Jamba-Reasoning-3B
6-bit
Text generation · AI21 · Jamba ↓ 50 · ♥ 1
Params
3.0B
Weights
≈ 2.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

DeepSeek-v3-0324-8bit

from deepseek-ai/DeepSeek-v3-0324
8-bit
Text generation · DeepSeek ↓ 50 · ♥ 1
Params
671B
Weights
≈ 713 GB
Mac memory
> 512 GB

mit · updated 2025-04-02

Falcon-H1-Tiny-Coder-90M-8bit

from tiiuae/Falcon-H1-Tiny-Coder-90M
8-bit
Text generation · TII · Falcon ↓ 50 · ♥ 1
Params
91M
Weights
≈ 97 MB
Mac memory
8 GB+

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

Qwen2-57B-A14B-Instruct-8bit

mlx-community/Qwen2-57B-A14B-Instruct-8bit
8-bit
Text generation ↓ 50 · ♥ 1
Params
57B
Weights
≈ 61.0 GB
Mac memory
96 GB+

apache-2.0 · updated 2024-06-06

Tmax-9B-MLX-4bit

from allenai/tmax-9b
4-bit
Text generation · Ai2 · OLMo ↓ 50 · ♥ 1
Params
9.0B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-25

Bio-Medical-Llama-3-8B-4bit

from ContactDoctor/Bio-Medical-Llama-3-8B
4-bit
Text generation · ContactDoctor ↓ 50 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

other · updated 2025-06-03

Falcon-H1R-7B-6bit

from tiiuae/Falcon-H1R-7B
6-bit
Text generation · TII · Falcon ↓ 50 · ♥ 0
Params
7.6B
Weights
≈ 6.2 GB
Mac memory
16 GB+

falcon-llm-license · updated 2026-01-05

HY-MT1.5-7B-8bit

from tencent/HY-MT1.5-7B
8-bit
Text generation · tencent ↓ 50 · ♥ 0
Params
7.5B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2026-01-03

Huihui-gemma-3-270m-it-abliterated-4bit

from huihui-ai/Huihui-gemma-3-270m-it-abliterated
4-bit
Text generation · huihui-ai ↓ 50 · ♥ 0
Params
268M
Weights
≈ 151 MB
Mac memory
8 GB+

gemma · updated 2025-09-27

Llama-3.1-Tulu-3-70B-6bit

from allenai/Llama-3.1-Tulu-3-70B
6-bit
Text generation · Ai2 · OLMo ↓ 50 · ♥ 0
Params
71B
Weights
≈ 57.3 GB
Mac memory
96 GB+

llama3.1 · updated 2024-11-25

Mellum-4b-sft-python-8bit

from JetBrains/Mellum-4b-sft-python
8-bit
Text generation · JetBrains ↓ 50 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-28

Meta-Llama-3.1-8B-8bit

mlx-community/Meta-Llama-3.1-8B-8bit
8-bit
Text generation ↓ 50 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.1 · updated 2024-07-23

OLMo-2-1124-13B-Instruct-6bit

from allenai/OLMo-2-1124-13B-Instruct
6-bit
Text generation · Ai2 · OLMo ↓ 50 · ♥ 0
Params
14B
Weights
≈ 11.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-11-27

Qwen2.5-3B-bf16

mlx-community/Qwen2.5-3B-bf16
bf16
Text generation ↓ 50 · ♥ 0
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

qwen-research · updated 2024-09-18

Seed-Coder-8B-Reasoning-bf16-mlx-8Bit

from ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16
8-bit
Text generation · ByteDance-Seed ↓ 50 · ♥ 0
Params
8.3B
Weights
≈ 8.8 GB
Mac memory
16 GB+

mit · updated 2025-07-18

granite-3b-code-instruct-8bit

from ibm-granite/granite-3b-code-base-2k
8-bit
Text generation · IBM · Granite ↓ 50 · ♥ 0
Params
3.5B
Weights
≈ 3.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-05-06

llm-jp-3-3.7b-instruct

mlx-community/llm-jp-3-3.7b-instruct
Text generation ↓ 50 · ♥ 0
Params
3.8B
Weights
≈ 7.6 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-09-25

llm-jp-3.1-13b-instruct4-8bit

from llm-jp/llm-jp-3.1-13b-instruct4
8-bit
Text generation · llm-jp ↓ 50 · ♥ 0
Params
14B
Weights
≈ 14.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-16

DeepCoder-14B-Preview-4bit

from agentica-org/DeepCoder-14B-Preview
4-bit
Text generation · agentica-org ↓ 49 · ♥ 2
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

mit · updated 2025-04-08

Laguna-XS.2-mxfp8

from poolside/Laguna-XS.2
MXFP8
Text generation · poolside ↓ 49 · ♥ 2
Params
33B
Weights
≈ 35.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-28

ERNIE-4.5-21B-A3B-PT-5bit

from baidu/ERNIE-4.5-21B-A3B-PT
5-bit
Text generation · baidu ↓ 49 · ♥ 1
Params
22B
Weights
≈ 15.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-04

Falcon-E-3B-Instruct-1.58bit

from tiiuae/Falcon-E-3B-Instruct
58-bit
Text generation · TII · Falcon ↓ 49 · ♥ 1
Params
864M
Weights
≈ 999 MB
Mac memory
8 GB+

falcon-llm-license · updated 2025-06-10

JOSIE-TinyLlama-1.1B-32k-base-4bit

from Doctor-Shotgun/TinyLlama-1.1B-32k
4-bit
Text generation · Doctor-Shotgun ↓ 49 · ♥ 1
Params
1.1B
Weights
≈ 619 MB
Mac memory
8 GB+

updated 2024-05-24

Josiefied-Qwen3-1.7B-abliterated-v1-bf16

from Goekdeniz-Guelmez/Josiefied-Qwen3-1.7B-abliterated-v1
bf16
Text generation · Goekdeniz-Guelmez ↓ 49 · ♥ 1
Params
1.7B
Weights
≈ 3.4 GB
Mac memory
8 GB+

updated 2025-04-29

Maxine-34B-stock

from louisbrulenaudet/Maxine-34B-stock
Text generation · louisbrulenaudet ↓ 49 · ♥ 1
Params
34B
Weights
≈ 137 GB
Mac memory
192 GB+

updated 2024-07-10

Qwen3.6-27B-MTP-5bit

from Qwen/Qwen3.6-27B
5-bit
Text generation · Qwen ↓ 49 · ♥ 1
Params
425M
Weights
≈ 292 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

EXAONE-Deep-7.8B-4bit

from LGAI-EXAONE/EXAONE-Deep-7.8B
4-bit
Text generation · LGAI-EXAONE ↓ 49 · ♥ 0
Params
7.8B
Weights
≈ 4.4 GB
Mac memory
8 GB+

exaone · updated 2025-03-18

GLM-4-32B-Base-0414-8bit

from zai-org/GLM-4-32B-Base-0414
8-bit
Text generation · zai-org ↓ 49 · ♥ 0
Params
33B
Weights
≈ 34.6 GB
Mac memory
48 GB+

mit · updated 2025-04-21

Llama-3.1-Swallow-70B-Instruct-v0.3-8bit

from tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
8-bit
Text generation · tokyotech-llm ↓ 49 · ♥ 0
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3.1 · updated 2025-03-10

Qwen2-72B-Instruct-unquantized

mlx-community/Qwen2-72B-Instruct-unquantized
Text generation ↓ 49 · ♥ 0
Params
73B
Weights
≈ 145 GB
Mac memory
192 GB+

tongyi-qianwen · updated 2024-06-07

RakutenAI-2.0-8x7B-MLX-4bit

from Rakuten/RakutenAI-2.0-8x7B
4-bit
Text generation · Rakuten ↓ 49 · ♥ 0
Params
47B
Weights
≈ 26.3 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-03-20

Yi-6B-Chat-8bit

from 01-ai/Yi-6B-Chat
8-bit
Text generation · 01.AI · Yi ↓ 49 · ♥ 0
Params
6.1B
Weights
≈ 6.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-11-05

gemma-4-26B-A4B-it-qat-assistant-5bit

from google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant
5-bit
Text generation · Google · Gemma ↓ 49 · ♥ 0
Params
420M
Weights
≈ 289 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

karakuri-lm-8x7b-instruct-v0.1

from karakuri-ai/karakuri-lm-8x7b-instruct-v0.1
Text generation · karakuri-ai ↓ 49 · ♥ 0
Params
47B
Weights
≈ 93.4 GB
Mac memory
128 GB+

apache-2.0 · updated 2024-10-11

llama3-8b-cpt-sahabatai-v1-instruct-8bit

from GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
8-bit
Text generation · GoToCompany ↓ 49 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3 · updated 2026-06-06

phi-4-abliterated-2bit

from huihui-ai/phi-4-abliterated
2-bit
Text generation · huihui-ai ↓ 49 · ♥ 0
Params
15B
Weights
≈ 4.6 GB
Mac memory
8 GB+

mit · updated 2025-01-09

QwQ-32B-bf16

from Qwen/QwQ-32B
bf16
Text generation · Qwen ↓ 48 · ♥ 9
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-03-05

Orchestrator-8B-4bit

from nvidia/Nemotron-Orchestrator-8B
4-bit
Text generation · NVIDIA ↓ 48 · ♥ 5
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

updated 2025-11-29

IQuest-Coder-V1-40B-Loop-Instruct-6bit

from IQuestLab/IQuest-Coder-V1-40B-Loop-Instruct
6-bit
Text generation · IQuestLab ↓ 48 · ♥ 3
Params
40B
Weights
≈ 32.3 GB
Mac memory
48 GB+

iquestcoder · updated 2026-01-07

Llama-3-70B-Instruct-Gradient-1048k-2bit

mlx-community/Llama-3-70B-Instruct-Gradient-1048k-2bit
2-bit
Text generation ↓ 48 · ♥ 2
Params
71B
Weights
≈ 22.1 GB
Mac memory
32 GB+

llama3 · updated 2024-05-04

Meta-Llama-3-8B-Instruct

mlx-community/Meta-Llama-3-8B-Instruct
Text generation ↓ 48 · ♥ 2
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3 · updated 2024-04-26

Qwen1.5-7B-Chat-4bit

mlx-community/Qwen1.5-7B-Chat-4bit
4-bit
Text generation ↓ 48 · ♥ 2
Params
7.7B
Weights
≈ 5.2 GB
Mac memory
8 GB+

tongyi-qianwen · updated 2024-03-07

c4ai-command-r-08-2024-8bit

mlx-community/c4ai-command-r-08-2024-8bit
8-bit
Text generation ↓ 48 · ♥ 2
Params
32B
Weights
≈ 34.3 GB
Mac memory
48 GB+

cc-by-nc-4.0 · updated 2024-08-31

CodeLlama-7b-Instruct-hf-8bit-mlx

from codellama/CodeLlama-7b-Instruct-hf
8-bit
Text generation · codellama ↓ 48 · ♥ 1
Params
6.7B
Weights
≈ 7.2 GB
Mac memory
16 GB+

llama2 · updated 2025-04-27

LongCat-Flash-Lite-8bit

from meituan-longcat/LongCat-Flash-Lite
8-bit
Text generation · meituan-longcat ↓ 48 · ♥ 1
Params
69B
Weights
≈ 72.8 GB
Mac memory
96 GB+

mit · updated 2026-01-29

MiniMax-M2.7-nvfp4

from MiniMaxAI/MiniMax-M2.7
4-bit
Text generation · MiniMaxAI ↓ 48 · ♥ 1
Params
229B
Weights
≈ 129 GB
Mac memory
192 GB+

modified-mit · updated 2026-04-12

aya-23-35B-4bit

mlx-community/aya-23-35B-4bit
4-bit
Text generation ↓ 48 · ♥ 1
Params
35B
Weights
≈ 19.7 GB
Mac memory
24 GB+

cc-by-nc-4.0 · updated 2024-05-23

c4ai-command-r7b-12-2024-3bit

from CohereLabs/c4ai-command-r7b-12-2024
3-bit
Text generation · Cohere ↓ 48 · ♥ 1
Params
8.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2024-12-17

CodeLlama-13b-hf-8bit-mlx

from codellama/CodeLlama-13b-hf
8-bit
Text generation · codellama ↓ 48 · ♥ 0
Params
13B
Weights
≈ 13.8 GB
Mac memory
24 GB+

llama2 · updated 2025-04-27

Falcon-H1-Tiny-90M-Instruct-4bit

from tiiuae/Falcon-H1-Tiny-90M-Instruct
4-bit
Text generation · TII · Falcon ↓ 48 · ♥ 0
Params
91M
Weights
≈ 51 MB
Mac memory
8 GB+

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

Falcon3-Mamba-7B-Instruct-4bits

from tiiuae/Falcon3-Mamba-7B-Instruct
4-bit
Text generation · TII · Falcon ↓ 48 · ♥ 0
Params
7.3B
Weights
≈ 4.1 GB
Mac memory
8 GB+

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

Huihui-gemma-3n-E4B-it-abliterated-lm-6bit

from huihui-ai/Huihui-gemma-3n-E4B-it-abliterated
6-bit
Text generation · huihui-ai ↓ 48 · ♥ 0
Params
6.9B
Weights
≈ 5.6 GB
Mac memory
16 GB+

gemma · updated 2025-09-26

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

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-3B-Instruct-abliterated-v1
Text generation · Goekdeniz-Guelmez ↓ 48 · ♥ 0
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-12-20

KwaiCoder-AutoThink-preview-3bit

from Kwaipilot/KwaiCoder-AutoThink-preview
3-bit
Text generation · Kwaipilot ↓ 48 · ♥ 0
Params
41B
Weights
≈ 17.7 GB
Mac memory
24 GB+

kwaipilot-license · updated 2025-06-09

Llama-3.1-Swallow-8B-Instruct-v0.2-4bit

from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2
4-bit
Text generation · tokyotech-llm ↓ 48 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3.1 · updated 2024-11-11