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 2h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

2,922 builds · page 13 of 49 · clear filters

K2-Horizon-7B-8bit

from IFM/K2-Horizon-7B
8-bit
Text generation · IFM ↓ 148 · ♥ 0
Params
9.0B
Weights
≈ 9.6 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-30

Ornith-1.0-35B-OptiQ-4bit-REAP-19B

from mlx-community/Ornith-1.0-35B-OptiQ-4bit
4-bit
Text generation ↓ 147 · ♥ 2
Params
19B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-15

plamo-2-translate-bf16

from pfnet/plamo-2-translate
bf16
Text generation · pfnet ↓ 147 · ♥ 1
Params
9.5B
Weights
≈ 19.1 GB
Mac memory
24 GB+

plamo-community-license · updated 2026-10-07

MiniCPM5-2B-bf16

from openbmb/MiniCPM5-2B
bf16
Text generation · openbmb ↓ 147 · ♥ 0
Params
2.5B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-10

aya-expanse-8b-4bit

from CohereLabs/aya-expanse-8b
4-bit
Text generation · Cohere ↓ 147 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2024-10-24

gemma-3-1b-it-8bit

from google/gemma-3-1b-it
8-bit
Text generation · Google · Gemma ↓ 146 · ♥ 5
Params
1.3B
Weights
≈ 1.4 GB
Mac memory
8 GB+

gemma · updated 2025-03-12

granite-4.1-3b-mxfp4

from ibm-granite/granite-4.1-3b
MXFP4
Text generation · IBM · Granite ↓ 146 · ♥ 5
Params
3.4B
Weights
≈ 1.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-30

Devstral-2-123B-Instruct-2512-8bit

from mistralai/Devstral-2-123B-Instruct-2512
8-bit
Text generation · Mistral ↓ 146 · ♥ 1
Params
125B
Weights
≈ 133 GB
Mac memory
192 GB+

other · updated 2025-12-10

Midnight-Miqu-70B-v1.5-MLX-8Bit

from sophosympatheia/Midnight-Miqu-70B-v1.5
8-bit
Text generation · sophosympatheia ↓ 145 · ♥ 2
Params
69B
Weights
≈ 73.3 GB
Mac memory
96 GB+

other · updated 2025-01-22

Qwen2.5-1.5B-Instruct-8bit

from Qwen/Qwen2.5-1.5B
8-bit
Text generation · Qwen ↓ 145 · ♥ 2
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Ministral-3-14B-Instruct-2512

from mistralai/Ministral-3-14B-Instruct-2512
Text generation · Mistral ↓ 145 · ♥ 1
Params
14B
Weights
≈ 27.0 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-12-03

gpt-oss-20b-Ja-Fin-Thinking-MLX-8bit

from nri-ai/gpt-oss-20b-Ja-Fin-Thinking
8-bit
Text generation · nri-ai ↓ 145 · ♥ 1
Params
21B
Weights
≈ 22.2 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-03-27

EXAONE-4.0-32B-4bit

from LGAI-EXAONE/EXAONE-4.0-32B
4-bit
Text generation · LGAI-EXAONE ↓ 144 · ♥ 2
Params
32B
Weights
≈ 18.0 GB
Mac memory
24 GB+

exaone · updated 2025-07-15

Qwen2.5-Coder-1.5B-bf16

from Qwen/Qwen2.5-1.5B
bf16
Text generation · Qwen ↓ 144 · ♥ 1
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Josiefied-Qwen3-14B-abliterated-v3-6bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3
6-bit
Text generation · Goekdeniz-Guelmez ↓ 144 · ♥ 0
Params
15B
Weights
≈ 12.0 GB
Mac memory
16 GB+

updated 2025-06-04

Qwen2.5-0.5B-4bit

mlx-community/Qwen2.5-0.5B-4bit
4-bit
Text generation ↓ 144 · ♥ 0
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Step-3.7-Flash-4bit

from stepfun-ai/Step-3.7-Flash
4-bit
Text generation · stepfun-ai ↓ 143 · ♥ 5
Params
197B
Weights
≈ 111 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-05-29

Mellum2-12B-A2.5B-Instruct-4bit

from JetBrains/Mellum2-12B-A2.5B-Instruct
4-bit
Text generation · JetBrains ↓ 143 · ♥ 2
Params
12B
Weights
≈ 6.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-08-11

NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-BF16

from nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
bf16
Text generation · NVIDIA ↓ 143 · ♥ 0
Params
32B
Weights
≈ 63.2 GB
Mac memory
96 GB+

nvidia-open-model-license · updated 2025-12-17

granite-4.0-350m-4bit

from ibm-granite/granite-4.0-350m
4-bit
Text generation · IBM · Granite ↓ 143 · ♥ 0
Params
352M
Weights
≈ 198 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

Granite-4.0-H-Tiny-4bit-DWQ

from ibm-granite/granite-4.0-h-tiny
4-bit DWQ
Text generation · IBM · Granite ↓ 142 · ♥ 5
Params
6.9B
Weights
≈ 3.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-03

Hermes-3-Llama-3.1-8B-MLX

from NousResearch/Hermes-3-Llama-3.1-8B
Text generation · NousResearch ↓ 142 · ♥ 1
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3 · updated 2025-04-29

LFM2-2.6B-Transcript-4bit

from LiquidAI/LFM2-2.6B-Transcript
4-bit
Text generation · LiquidAI ↓ 142 · ♥ 1
Params
2.6B
Weights
≈ 1.4 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-07

Qwen3-Coder-Next-mxfp8

from Qwen/Qwen3-Coder-Next
MXFP8
Text generation · Qwen ↓ 142 · ♥ 1
Params
80B
Weights
≈ 84.7 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-05-06

CodeLlama-13b-Instruct-hf-4bit-MLX

mlx-community/CodeLlama-13b-Instruct-hf-4bit-MLX
4-bit
Text generation ↓ 141 · ♥ 3
Params
—
Weights
—
Mac memory
—

llama2 · updated 2024-02-02

Qwen2.5-Coder-32B-4bit

from Qwen/Qwen2.5-Coder-32B
4-bit
Text generation · Qwen ↓ 141 · ♥ 3
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-11-12

phi-4-bf16

from microsoft/phi-4
bf16
Text generation · Microsoft · Phi ↓ 141 · ♥ 2
Params
15B
Weights
≈ 29.3 GB
Mac memory
48 GB+

mit · updated 2025-01-12

Dolphin-Mistral-24B-Venice-Edition-6bit

from dphn/Dolphin-Mistral-24B-Venice-Edition
6-bit
Text generation · dphn ↓ 141 · ♥ 1
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-06

Qwen3-8B-Base-bf16

from Qwen/Qwen3-8B-Base
bf16
Text generation · Qwen ↓ 141 · ♥ 1
Params
8.2B
Weights
≈ 16.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-05-03

Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr4e7

from Qwen/Qwen3-Coder-30B-A3B-Instruct
8-bit DWQ
Text generation · Qwen ↓ 141 · ♥ 0
Params
31B
Weights
≈ 32.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-08-01

K2-Horizon-7B-Uno-oQ6e

from IFM/K2-Horizon-7B-Uno
6-bit
Text generation · IFM ↓ 140 · ♥ 3
Params
9.0B
Weights
≈ 7.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-10

Qwen3.5-9B-MTP-bf16

from Qwen/Qwen3.5-9B
bf16
Text generation · Qwen ↓ 140 · ♥ 2
Params
243M
Weights
≈ 487 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

HY-MT1.5-7B-4bit

from tencent/HY-MT1.5-7B
4-bit
Text generation · tencent ↓ 140 · ♥ 0
Params
7.5B
Weights
≈ 4.2 GB
Mac memory
8 GB+

updated 2026-01-03

Kimi-K2.5-3bit

from moonshotai/Kimi-K2.5
3-bit
Text generation · Moonshot · Kimi ↓ 140 · ♥ 0
Params
1.0T
Weights
≈ 449 GB
Mac memory
512 GB+

modified-mit · updated 2026-02-07

NVIDIA-Nemotron-3-Nano-4B-8bit

from nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
8-bit
Text generation · NVIDIA ↓ 140 · ♥ 0
Params
4.0B
Weights
≈ 4.2 GB
Mac memory
8 GB+

nvidia-nemotron-open-model-license · updated 2026-03-20

Seed-OSS-36B-Instruct-4bit

from ByteDance-Seed/Seed-OSS-36B-Instruct
4-bit
Text generation · ByteDance-Seed ↓ 139 · ♥ 3
Params
36B
Weights
≈ 20.3 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-08-21

Hermes-4-14B-8bit

from NousResearch/Hermes-4-14B
8-bit
Text generation · NousResearch ↓ 139 · ♥ 2
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-09-03

CodeLlama-7b-Python-mlx

mlx-community/CodeLlama-7b-Python-mlx
Text generation ↓ 138 · ♥ 10
Params
—
Weights
—
Mac memory
—

llama2 · updated 2024-02-27

Qwen2.5-Coder-32B-8bit

from Qwen/Qwen2.5-Coder-32B
8-bit
Text generation · Qwen ↓ 138 · ♥ 4
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-11-12

NeoHorse-1-4B-4bit

from TokenRhythm/NeoHorse-1-4B
4-bit
Text generation · TokenRhythm ↓ 138 · ♥ 3
Params
4.2B
Weights
≈ 2.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-14

K2-Horizon-3.7B-8bit

from IFM/K2-Horizon-3.7B
8-bit
Text generation · IFM ↓ 138 · ♥ 0
Params
5.1B
Weights
≈ 5.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-30

Qwen3-4B-Thinking-2507-8bit

from Qwen/Qwen3-4B-Thinking-2507
8-bit
Text generation · Qwen ↓ 138 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-06

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

from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
4-bit DWQ
Text generation · DeepSeek ↓ 137 · ♥ 8
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

mit · updated 2025-05-29

Laguna-S-2.1-OptiQ-2bit

from poolside/Laguna-S-2.1
2-bit
Text generation · poolside ↓ 137 · ♥ 3
Params
118B
Weights
≈ 36.8 GB
Mac memory
48 GB+

openmdw-1.1 · updated 2026-09-15

XYZ-Aquila-mini-OptiQ-4bit-REAP-18B

from mlx-community/XYZ-Aquila-mini-OptiQ-4bit
4-bit
Text generation ↓ 137 · ♥ 2
Params
19B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-15

gemma-3n-E2B-it-text-4bit-dwq

from google/gemma-3n-E2B-it
4-bit DWQ
Text generation · Google · Gemma ↓ 137 · ♥ 1
Params
4.5B
Weights
≈ 5.2 GB
Mac memory
8 GB+

gemma · updated 2025-07-27

Qwen3-30B-A3B-4bit-DWQ-0508

from Qwen/Qwen3-30B-A3B
4-bit DWQ
Text generation · Qwen ↓ 136 · ♥ 14
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-05-08

gemma-2-2b-it

mlx-community/gemma-2-2b-it
Text generation ↓ 136 · ♥ 8
Params
2.6B
Weights
≈ 5.2 GB
Mac memory
8 GB+

gemma · updated 2024-11-06

codegemma-7b-it-8bit

mlx-community/codegemma-7b-it-8bit
8-bit
Text generation ↓ 136 · ♥ 6
Params
8.5B
Weights
≈ 9.8 GB
Mac memory
16 GB+

gemma · updated 2024-04-09

Kimi-Linear-48B-A3B-Instruct-6bit

from moonshotai/Kimi-Linear-48B-A3B-Instruct
6-bit
Text generation · Moonshot · Kimi ↓ 136 · ♥ 3
Params
49B
Weights
≈ 39.9 GB
Mac memory
48 GB+

mit · updated 2026-01-22

gemma-2-9b-4bit

mlx-community/gemma-2-9b-4bit
4-bit
Text generation ↓ 136 · ♥ 2
Params
9.2B
Weights
≈ 5.2 GB
Mac memory
8 GB+

gemma · updated 2024-06-27

Phi-4-mini-instruct-mlx-6Bit

from microsoft/Phi-4-mini-instruct
6-bit
Text generation · Microsoft · Phi ↓ 136 · ♥ 1
Params
3.8B
Weights
≈ 3.1 GB
Mac memory
8 GB+

mit · updated 2026-07-27

quantized-gemma-2b

mlx-community/quantized-gemma-2b
Text generation ↓ 135 · ♥ 8
Params
2.5B
Weights
≈ 9.0 GB
Mac memory
16 GB+

gemma-terms-of-use · updated 2024-02-21

CodeLlama-7b-Instruct-hf-4bit-MLX

mlx-community/CodeLlama-7b-Instruct-hf-4bit-MLX
4-bit
Text generation ↓ 135 · ♥ 3
Params
—
Weights
—
Mac memory
—

llama2 · updated 2024-01-30

Hermes-3-Llama-3.2-3B-4bit

from NousResearch/Hermes-3-Llama-3.2-3B
4-bit
Text generation · NousResearch ↓ 135 · ♥ 1
Params
3.2B
Weights
≈ 1.8 GB
Mac memory
8 GB+

llama3 · updated 2024-12-11

Agents-A1-OptiQ-4bit-REAP-19B

from mlx-community/Agents-A1-OptiQ-4bit
4-bit
Text generation ↓ 135 · ♥ 0
Params
19B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-15