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 3 of 49 · clear filters

Kimi-K3-mlx-reap160-2bit

from moonshotai/Kimi-K3
2-bit
Text generation · Moonshot · Kimi ↓ 1.6K · ♥ 2
Params
543B
Weights
≈ 170 GB
Mac memory
256 GB+

other · updated 2026-08-03

Qwen2.5-Coder-7B-Instruct-8bit

from Qwen/Qwen2.5-Coder-7B
8-bit
Text generation · Qwen ↓ 1.5K · ♥ 1
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-09-18

MiniCPM5-1B-OptiQ-4bit

from openbmb/MiniCPM5-1B
4-bit
Text generation · openbmb ↓ 1.5K · ♥ 11
Params
1.1B
Weights
≈ 608 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-14

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

from google/gemma-3n-E4B-it
4-bit
Text generation · Google · Gemma ↓ 1.5K · ♥ 8
Params
6.9B
Weights
≈ 3.9 GB
Mac memory
8 GB+

gemma · updated 2025-06-29

translategemma-12b-it-4bit

from google/translategemma-12b-it
4-bit
Text generation · Google · Gemma ↓ 1.5K · ♥ 6
Params
12B
Weights
≈ 6.6 GB
Mac memory
16 GB+

gemma · updated 2026-01-16

Llama-3.2-3B-Instruct-bf16

mlx-community/Llama-3.2-3B-Instruct-bf16
bf16
Text generation ↓ 1.5K · ♥ 5
Params
3.2B
Weights
≈ 6.4 GB
Mac memory
16 GB+

llama3.2 · updated 2024-09-26

Qwen3-0.6B-Base-4bit

from Qwen/Qwen3-0.6B-Base
4-bit
Text generation · Qwen ↓ 1.5K · ♥ 0
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-25

phi-4-4bit

from microsoft/phi-4
4-bit
Text generation · Microsoft · Phi ↓ 1.4K · ♥ 23
Params
15B
Weights
≈ 8.2 GB
Mac memory
16 GB+

mit · updated 2025-01-12

Qwen3-Next-80B-A3B-Instruct-4bit

from Qwen/Qwen3-Next-80B-A3B-Instruct
4-bit
Text generation · Qwen ↓ 1.4K · ♥ 25
Params
80B
Weights
≈ 44.8 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-09-12

Spark-X2.6-4B-OptiQ-4bit

from XHToken/Spark-X2.6-4B
4-bit
Text generation · XHToken ↓ 1.4K · ♥ 3
Params
4.1B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-24

Qwen3.5-2B-OptiQ-4bit

from Qwen/Qwen3.5-2B
4-bit
Text generation · Qwen ↓ 1.4K · ♥ 14
Params
1.9B
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-30

Qwen2.5-Coder-14B-Instruct-abliterated-4bit

from huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated
4-bit
Text generation · huihui-ai ↓ 1.4K · ♥ 0
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-02-22

gemma-4-26B-A4B-it-OptiQ-4bit-REAP-14B

from mlx-community/gemma-4-26B-A4B-it-OptiQ-4bit
4-bit
Text generation ↓ 1.4K · ♥ 7
Params
14B
Weights
≈ 8.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-18

Llama-3.3-70B-Instruct-3bit

from meta-llama/Llama-3.3-70B-Instruct
3-bit
Text generation · Meta · Llama ↓ 1.4K · ♥ 8
Params
71B
Weights
≈ 30.9 GB
Mac memory
48 GB+

llama3.3 · updated 2024-12-06

MiniCPM5-1B-mlx-6Bit

from openbmb/MiniCPM5-1B
6-bit
Text generation · openbmb ↓ 1.4K · ♥ 0
Params
1.1B
Weights
≈ 878 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-10

Qwen3-Coder-30B-A3B-Instruct-8bit

from Qwen/Qwen3-Coder-30B-A3B-Instruct
8-bit
Text generation · Qwen ↓ 1.4K · ♥ 11
Params
31B
Weights
≈ 32.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-07-31

MiniMax-M3.1-Flash-Text-4bit

from MiniMaxAI/MiniMax-M3.1-Flash
4-bit
Text generation · MiniMaxAI ↓ 1.3K · ♥ 5
Params
426B
Weights
≈ 243 GB
Mac memory
512 GB+

minimax-community · updated 2026-10-23

Josiefied-Qwen3-8B-abliterated-v1-4bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
4-bit
Text generation · Goekdeniz-Guelmez ↓ 1.3K · ♥ 5
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

updated 2025-05-01

Qwen2.5-Coder-1.5B-4bit

from Qwen/Qwen2.5-1.5B
4-bit
Text generation · Qwen ↓ 1.3K · ♥ 3
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Mellum2.1-12B-A2.5B-Thinking-6bit

from JetBrains/Mellum2.1-12B-A2.5B-Thinking
6-bit
Text generation · JetBrains ↓ 1.3K · ♥ 3
Params
12B
Weights
≈ 9.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-11

Meta-Llama-3.1-70B-Instruct-4bit

mlx-community/Meta-Llama-3.1-70B-Instruct-4bit
4-bit
Text generation ↓ 1.3K · ♥ 6
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+

llama3.1 · updated 2024-11-26

OLMo-2-0325-32B-Instruct-4bit

from allenai/OLMo-2-0325-32B-Instruct
4-bit
Text generation · Ai2 · OLMo ↓ 1.3K · ♥ 10
Params
32B
Weights
≈ 18.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-14

OLMoE-1B-7B-0125-Instruct-4bit

from allenai/OLMoE-1B-7B-0125-Instruct
4-bit
Text generation · Ai2 · OLMo ↓ 1.3K · ♥ 3
Params
6.9B
Weights
≈ 3.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-04

Qwen3-Coder-30B-A3B-Instruct-6bit

from Qwen/Qwen3-Coder-30B-A3B-Instruct
6-bit
Text generation · Qwen ↓ 1.3K · ♥ 2
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

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

from Qwen/Qwen3.6-35B-A3B
4-bit
Text generation · Qwen ↓ 1.3K · ♥ 6
Params
845M
Weights
≈ 475 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

Qwen3.5-0.8B-OptiQ-4bit

from Qwen/Qwen3.5-0.8B
4-bit
Text generation · Qwen ↓ 1.3K · ♥ 24
Params
752M
Weights
≈ 424 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-30

GLM-4.7-Flash-8bit

from zai-org/GLM-4.7-Flash
8-bit
Text generation · zai-org ↓ 1.3K · ♥ 26
Params
30B
Weights
≈ 31.8 GB
Mac memory
48 GB+

mit · updated 2026-01-25

Qwen3-235B-A22B-8bit

from Qwen/Qwen3-235B-A22B
8-bit
Text generation · Qwen ↓ 1.3K · ♥ 3
Params
235B
Weights
≈ 250 GB
Mac memory
512 GB+

apache-2.0 · updated 2025-04-29

Qwen2.5-Coder-7B-Instruct-MLX

from Qwen/Qwen2.5-Coder-7B-Instruct
Text generation · Qwen ↓ 1.3K · ♥ 6
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-03-24

Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B

from mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit
4-bit
Text generation ↓ 1.3K · ♥ 8
Params
19B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-30

Mistral-Small-4-119B-2603-OptiQ-2bit

from mistralai/Mistral-Small-4-119B-2603
2-bit
Text generation · Mistral ↓ 1.3K · ♥ 2
Params
119B
Weights
≈ 38.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-09-24

Nanbeige4.1-3B-8bit

from Nanbeige/Nanbeige4.1-3B
8-bit
Text generation · Nanbeige ↓ 1.3K · ♥ 15
Params
3.9B
Weights
≈ 4.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-11

gpt-oss-120b-MXFP4-Q4

from openai/gpt-oss-120b
MXFP4
Text generation · OpenAI · gpt-oss ↓ 1.3K · ♥ 7
Params
117B
Weights
≈ 65.8 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-08-29

gemma-4-26B-A4B-it-OptiQ-4bit

from google/gemma-4-26B-A4B-it
4-bit
Text generation · Google · Gemma ↓ 1.2K · ♥ 21
Params
25B
Weights
≈ 15.3 GB
Mac memory
24 GB+

gemma · updated 2026-10-18

Qwen2.5-Coder-7B-4bit

from Qwen/Qwen2.5-7B
4-bit
Text generation · Qwen ↓ 1.2K · ♥ 0
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Kimi-K2-Instruct-4bit

from moonshotai/Kimi-K2-Instruct
4-bit
Text generation · Moonshot · Kimi ↓ 1.2K · ♥ 13
Params
1.0T
Weights
≈ 578 GB
Mac memory
> 512 GB

modified-mit · updated 2025-07-11

granite-4.1-3b-4bit

from ibm-granite/granite-4.1-3b
4-bit
Text generation · IBM · Granite ↓ 1.2K · ♥ 0
Params
3.4B
Weights
≈ 1.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-01

Hermes-4-14B-4bit

from NousResearch/Hermes-4-14B
4-bit
Text generation · NousResearch ↓ 1.2K · ♥ 6
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-09-03

Laguna-S-2.1-oQ4e

from poolside/Laguna-S-2.1
4-bit
Text generation · poolside ↓ 1.2K · ♥ 10
Params
118B
Weights
≈ 66.2 GB
Mac memory
96 GB+

openmdw-1.1 · updated 2026-07-24

Mistral-Large-4-1T-A52B-Text-4bit

from mistralai/Mistral-Large-4-1T-A52B
4-bit
Text generation · Mistral ↓ 1.2K · ♥ 1
Params
1.0T
Weights
≈ 590 GB
Mac memory
> 512 GB

mistral-ecosystem-open-weight-license · updated 2026-10-29

gemma-4-E4B-it-assistant-bf16

from google/gemma-4-E4B-it-assistant
bf16
Text generation · Google · Gemma ↓ 1.2K · ♥ 13
Params
79M
Weights
≈ 159 MB
Mac memory
8 GB+

gemma · updated 2026-05-05

Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit

from mistralai/Devstral-Small-2-24B-Instruct-2512
4-bit
Text generation · Mistral ↓ 1.2K · ♥ 4
Params
24B
Weights
≈ 14.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-09-24

Arch-Router-1.5B-mlx-8Bit

from katanemo/Arch-Router-1.5B
8-bit
Text generation · katanemo ↓ 1.2K · ♥ 0
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

katanemo-research · updated 2025-10-17

LFM3-1.7B-OptiQ-4bit

from LiquidAI/LFM3-1.7B
4-bit
Text generation · LiquidAI ↓ 1.2K · ♥ 1
Params
1.7B
Weights
≈ 973 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-10-29

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

mlx-community/Qwen3.6-35B-A3B-4bit-DWQ
4-bit DWQ
Text generation ↓ 1.2K · ♥ 18
Params
35B
Weights
≈ 19.5 GB
Mac memory
24 GB+

updated 2026-04-17

flint-oQ4e

from RecursiveSI/flint
4-bit
Text generation · RecursiveSI ↓ 1.2K · ♥ 2
Params
40B
Weights
≈ 22.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-10-27

Qwen3-Coder-30B-A3B-Instruct-4bit-dwq-v2

from Qwen/Qwen3-Coder-30B-A3B-Instruct
4-bit DWQ
Text generation · Qwen ↓ 1.1K · ♥ 11
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-08-09

granite-4.0-h-micro-4bit

from ibm-granite/granite-4.0-h-micro
4-bit
Text generation · IBM · Granite ↓ 1.1K · ♥ 1
Params
3.2B
Weights
≈ 1.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-04

Qwen3-Coder-30B-A3B-Instruct-3bit

from Qwen/Qwen3-Coder-30B-A3B-Instruct
3-bit
Text generation · Qwen ↓ 1.1K · ♥ 2
Params
31B
Weights
≈ 13.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-31

humanizer-12b-OptiQ-4bit

from jialinyyzz/humanizer
4-bit
Text generation · jialinyyzz ↓ 1.1K · ♥ 6
Params
12B
Weights
≈ 6.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-18

Qwen3-4B-Instruct-2507-4bit-DWQ-2510

from Qwen/Qwen3-4B-Instruct-2507
4-bit DWQ
Text generation · Qwen ↓ 1.1K · ♥ 2
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-13

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

from huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
4-bit
Text generation · huihui-ai ↓ 1.1K · ♥ 1
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-01-06

Mistral-Large-4-1T-A52B-Text-2bit

from mistralai/Mistral-Large-4-1T-A52B
2-bit
Text generation · Mistral ↓ 1.1K · ♥ 1
Params
1.0T
Weights
≈ 328 GB
Mac memory
512 GB+

mistral-ecosystem-open-weight-license · updated 2026-10-29

granite-4.0-h-tiny-4bit

from ibm-granite/granite-4.0-h-micro
4-bit
Text generation · IBM · Granite ↓ 1.1K · ♥ 0
Params
6.9B
Weights
≈ 3.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-04

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

from google/gemma-4-E4B-it
4-bit
Text generation · Google · Gemma ↓ 1.1K · ♥ 29
Params
7.5B
Weights
≈ 5.2 GB
Mac memory
8 GB+

gemma · updated 2026-10-18

Qwen2.5-Coder-32B-Instruct-bf16

from Qwen/Qwen2.5-Coder-32B-Instruct
bf16
Text generation · Qwen ↓ 1.1K · ♥ 11
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2024-11-11