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 52m ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

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

Qwen3.6-35B-A3B-OptiQ-4bit

from Qwen/Qwen3.6-35B-A3B
4-bit
Text generation · Qwen ↓ 3.6K · ♥ 82
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-11-05

Qwen2.5-Coder-3B-Instruct-4bit

from Qwen/Qwen2.5-Coder-3B-Instruct
4-bit
Text generation · Qwen ↓ 3.6K · ♥ 6
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

qwen-research · updated 2024-11-11

SmolLM3-3B-4bit

from HuggingFaceTB/SmolLM3-3B
4-bit
Text generation · Hugging Face ↓ 3.5K · ♥ 7
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-08

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

mlx-community/Meta-Llama-3.1-8B-Instruct-8bit
8-bit
Text generation ↓ 3.2K · ♥ 10
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.1 · updated 2024-11-26

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

from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
4-bit
Text generation · DeepSeek ↓ 3.2K · ♥ 8
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

mit · updated 2025-05-30

Llama-3.2-3B-Instruct-8bit

mlx-community/Llama-3.2-3B-Instruct-8bit
8-bit
Text generation ↓ 3.0K · ♥ 2
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+

llama3.2 · updated 2024-09-26

MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit

from XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
4-bit
Text generation · XiaomiMiMo ↓ 3.0K · ♥ 18
Params
9.0B
Weights
≈ 5.0 GB
Mac memory
8 GB+

mit · updated 2026-09-27

gemma-4-12B-it-OptiQ-4bit

from google/gemma-4-12B-it
4-bit
Text generation · Google · Gemma ↓ 3.0K · ♥ 58
Params
12B
Weights
≈ 6.8 GB
Mac memory
16 GB+

gemma · updated 2026-10-18

Meta-Llama-3-8B-Instruct-4bit

mlx-community/Meta-Llama-3-8B-Instruct-4bit
4-bit
Text generation ↓ 3.0K · ♥ 84
Params
8.0B
Weights
≈ 5.3 GB
Mac memory
8 GB+

llama3 · updated 2024-04-19

MiniMax-M3.1-Flash-Text-3bit

from MiniMaxAI/MiniMax-M3.1-Flash
3-bit
Text generation · MiniMaxAI ↓ 2.9K · ♥ 2
Params
426B
Weights
≈ 186 GB
Mac memory
256 GB+

minimax-community · updated 2026-10-23

Qwen2.5-Coder-32B-Instruct-4bit

from Qwen/Qwen2.5-Coder-32B-Instruct
4-bit
Text generation · Qwen ↓ 2.9K · ♥ 14
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-11-11

Qwen3-Coder-Next-8bit

from Qwen/Qwen3-Coder-Next
8-bit
Text generation · Qwen ↓ 2.7K · ♥ 29
Params
80B
Weights
≈ 84.7 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-02-04

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

from Qwen/Qwen2.5-Coder-0.5B-Instruct
4-bit
Text generation · Qwen ↓ 2.7K · ♥ 6
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-11

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit

from nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
4-bit
Text generation · NVIDIA ↓ 2.6K · ♥ 7
Params
32B
Weights
≈ 17.8 GB
Mac memory
24 GB+

openmdw-1.1 · updated 2026-08-11

Llama-3.2-3B-Instruct-uncensored-6bit

from chuanli11/Llama-3.2-3B-Instruct-uncensored
6-bit
Text generation · chuanli11 ↓ 2.6K · ♥ 4
Params
3.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+

updated 2025-04-23

Phi-4-mini-instruct-4bit

from microsoft/Phi-4-mini-instruct
4-bit
Text generation · Microsoft · Phi ↓ 2.6K · ♥ 5
Params
3.8B
Weights
≈ 2.2 GB
Mac memory
8 GB+

mit · updated 2025-03-05

gemma-4-31B-it-qat-OptiQ-4bit

from google/gemma-4-31B-it-qat-q4_0-unquantized
4-bit
Text generation · Google · Gemma ↓ 2.6K · ♥ 12
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-18

gemma-2-2b-it-4bit

mlx-community/gemma-2-2b-it-4bit
4-bit
Text generation ↓ 2.5K · ♥ 2
Params
2.6B
Weights
≈ 1.5 GB
Mac memory
8 GB+

gemma · updated 2024-11-06

Qwen3.8-Flash-Next-OptiQ-2bit

from Qwen/Qwen3.8-Flash-Next
2-bit
Text generation · Qwen ↓ 2.5K · ♥ 4
Params
177B
Weights
≈ 56.3 GB
Mac memory
96 GB+

qwen-community-1.0 · updated 2026-09-27

Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B

from mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit
4-bit
Text generation ↓ 2.5K · ♥ 12
Params
19B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-30

gemma-3n-E2B-it-lm-4bit

from google/gemma-3n-E2B-it
4-bit
Text generation · Google · Gemma ↓ 2.5K · ♥ 3
Params
4.5B
Weights
≈ 2.5 GB
Mac memory
8 GB+

gemma · updated 2025-06-29

Llama-2-7b-chat-mlx

mlx-community/Llama-2-7b-chat-mlx
Text generation ↓ 2.4K · ♥ 85
Params
—
Weights
—
Mac memory
—

llama2 · updated 2023-12-20

Qwen2.5-Coder-32B-Instruct-8bit

from Qwen/Qwen2.5-Coder-32B-Instruct
8-bit
Text generation · Qwen ↓ 2.4K · ♥ 14
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-11-11

Llama-3.2-3B-Instruct

from meta-llama/Llama-3.2-3B-Instruct
Text generation · Meta · Llama ↓ 2.4K · ♥ 10
Params
3.2B
Weights
≈ 6.4 GB
Mac memory
16 GB+

llama3.2 · updated 2024-09-25

gpt-oss-20b-MXFP4-Q4

from openai/gpt-oss-20b
MXFP4
Text generation · OpenAI · gpt-oss ↓ 2.3K · ♥ 19
Params
21B
Weights
≈ 11.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-08-29

Qwen3.8-27B-MTP-8bit

from Qwen/Qwen3.8-27B
8-bit
Text generation · Qwen ↓ 2.3K · ♥ 19
Params
425M
Weights
≈ 451 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-11

gemma-4-e4b-it-qat-OptiQ-4bit

from google/gemma-4-E4B-it-qat-q4_0-unquantized
4-bit
Text generation · Google · Gemma ↓ 2.2K · ♥ 18
Params
7.5B
Weights
≈ 5.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-18

Qwen3.6-27B-OptiQ-4bit

from Qwen/Qwen3.6-27B
4-bit
Text generation · Qwen ↓ 2.2K · ♥ 82
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-30

GLM-5.3-4bit

from zai-org/GLM-5.3-BF16
4-bit
Text generation · zai-org ↓ 2.1K · ♥ 4
Params
743B
Weights
≈ 418 GB
Mac memory
512 GB+

glm-5.3 · updated 2026-09-02

Laguna-XS-2.1-4bit

from poolside/Laguna-XS-2.1
4-bit
Text generation · poolside ↓ 2.1K · ♥ 4
Params
33B
Weights
≈ 18.8 GB
Mac memory
24 GB+

openmdw-1.1 · updated 2026-07-03

DeepSeek-V4-Flash-0731-2.4bit-mixed

from deepseek-ai/DeepSeek-V4-Flash-0731
4-bit
Text generation · DeepSeek ↓ 2.0K · ♥ 30
Params
304B
Weights
≈ 171 GB
Mac memory
256 GB+

mit · updated 2026-08-05

Qwen2.5-32B-Instruct-4bit

from Qwen/Qwen2.5-32B
4-bit
Text generation · Qwen ↓ 2.0K · ♥ 4
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-09-18

SmolLM2-135M-Instruct-8bit

from mlx-community/SmolLM2-135M-Instruct
8-bit
Text generation ↓ 2.0K · ♥ 1
Params
135M
Weights
≈ 143 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-01

Qwen3-32B-4bit

from Qwen/Qwen3-32B
4-bit
Text generation · Qwen ↓ 2.0K · ♥ 7
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-04-29

Llama-3-Groq-8B-Tool-Use-4bit

mlx-community/Llama-3-Groq-8B-Tool-Use-4bit
4-bit
Text generation ↓ 2.0K · ♥ 20
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3 · updated 2024-07-17

Llama-3.2-1B-Instruct-8bit

mlx-community/Llama-3.2-1B-Instruct-8bit
8-bit
Text generation ↓ 2.0K · ♥ 1
Params
1.2B
Weights
≈ 1.3 GB
Mac memory
8 GB+

llama3.2 · updated 2024-09-26

Llama-3.2-1B-Instruct-bf16

mlx-community/Llama-3.2-1B-Instruct-bf16
bf16
Text generation ↓ 2.0K · ♥ 5
Params
1.2B
Weights
≈ 2.5 GB
Mac memory
8 GB+

llama3.2 · updated 2024-09-26

flint-OptiQ-4bit

from RecursiveSI/flint
4-bit
Text generation · RecursiveSI ↓ 1.9K · ♥ 5
Params
40B
Weights
≈ 22.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-10-24

LFM2.5-8B-A1B-MLX-4bit

from LiquidAI/LFM2.5-8B-A1B
4-bit
Text generation · LiquidAI ↓ 1.9K · ♥ 3
Params
8.5B
Weights
≈ 4.8 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

Qwen2.5-Coder-14B-Instruct-8bit

from Qwen/Qwen2.5-Coder-14B-Instruct
8-bit
Text generation · Qwen ↓ 1.9K · ♥ 2
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-11-11

gpt-oss-20b-OptiQ-4bit

from openai/gpt-oss-20b
4-bit
Text generation · OpenAI · gpt-oss ↓ 1.8K · ♥ 14
Params
21B
Weights
≈ 11.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-16

Qwen3-Coder-Next-6bit

from Qwen/Qwen3-Coder-Next
6-bit
Text generation · Qwen ↓ 1.8K · ♥ 3
Params
80B
Weights
≈ 64.7 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-02-04

Llama-3-8B-Instruct-1048k-4bit

mlx-community/Llama-3-8B-Instruct-1048k-4bit
4-bit
Text generation ↓ 1.8K · ♥ 25
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3 · updated 2024-04-29

LFM2.5-2.6B-4bit

from LiquidAI/LFM2.5-2.6B
4-bit
Text generation · LiquidAI ↓ 1.8K · ♥ 5
Params
2.7B
Weights
≈ 1.5 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

Josiefied-Qwen3-1.7B-abliterated-v1-4bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-1.7B-abliterated-v1
4-bit
Text generation · Goekdeniz-Guelmez ↓ 1.8K · ♥ 3
Params
1.7B
Weights
≈ 968 MB
Mac memory
8 GB+

updated 2025-04-29

DeepSeek-V3-0324-4bit

from deepseek-ai/DeepSeek-v3-0324
4-bit
Text generation · DeepSeek ↓ 1.8K · ♥ 40
Params
671B
Weights
≈ 378 GB
Mac memory
512 GB+

mit · updated 2025-08-20

MiniCPM5-2B-8bit

from openbmb/MiniCPM5-2B
8-bit
Text generation · openbmb ↓ 1.8K · ♥ 9
Params
2.5B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-10

Qwen2.5-7B-Instruct-Uncensored-4bit

from Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
4-bit
Text generation · Orion-zhen ↓ 1.8K · ♥ 8
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

gpl-3.0 · updated 2024-10-21

Kimi-Dev-72B-4bit-DWQ

from moonshotai/Kimi-Dev-72B
4-bit DWQ
Text generation · Moonshot · Kimi ↓ 1.8K · ♥ 22
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+

mit · updated 2025-07-12

Qwen2.5-0.5B-Instruct-bf16

from Qwen/Qwen2.5-0.5B
bf16
Text generation · Qwen ↓ 1.8K · ♥ 1
Params
494M
Weights
≈ 988 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

DeepSeek-R1-Distill-Llama-70B-4bit

from deepseek-ai/DeepSeek-R1-Distill-Llama-70B
4-bit
Text generation · DeepSeek ↓ 1.7K · ♥ 13
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+

updated 2025-02-26

Qwen3-4B-8bit

from Qwen/Qwen3-4B
8-bit
Text generation · Qwen ↓ 1.7K · ♥ 1
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

Mistral-Small-3.2-24B-Instruct-2506-4bit

from mlx-community/Mistral-Small-3.2-24B-Instruct-2506-bf16
4-bit
Text generation ↓ 1.7K · ♥ 1
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-21

Qwen3.6-35B-A3B-DFlash2-4bit

from incoai/Qwen3.6-35B-A3B-Splash
4-bit
Text generation · incoai ↓ 1.7K · ♥ 10
Params
526M
Weights
≈ 479 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-25

llama-3.3-70b-instruct-fp16

from meta-llama/Llama-3.3-70B-Instruct
fp16
Text generation · Meta · Llama ↓ 1.7K · ♥ 1
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+

llama3.3 · updated 2025-03-22

gemma-3-1b-it-bf16

from google/gemma-3-1b-it
bf16
Text generation · Google · Gemma ↓ 1.6K · ♥ 1
Params
1.3B
Weights
≈ 2.6 GB
Mac memory
8 GB+

gemma · updated 2025-03-12

gemma-3-270m-it-4bit

from google/gemma-3-270m-it
4-bit
Text generation · Google · Gemma ↓ 1.6K · ♥ 10
Params
268M
Weights
≈ 151 MB
Mac memory
8 GB+

gemma · updated 2025-08-14

Qwen3.5-397B-A17B-nvfp4

from Qwen/Qwen3.5-397B-A17B
4-bit
Text generation · Qwen ↓ 1.6K · ♥ 6
Params
396B
Weights
≈ 223 GB
Mac memory
256 GB+

apache-2.0 · updated 2026-02-16

Kimi-K2-Thinking

from moonshotai/Kimi-K2-Thinking
4-bit
Text generation · Moonshot · Kimi ↓ 1.6K · ♥ 17
Params
1.0T
Weights
≈ 594 GB
Mac memory
> 512 GB

modified-mit · updated 2025-11-07