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 16 of 49 · clear filters

CodeLlama-7b-Python-hf-4bit

mlx-community/CodeLlama-7b-Python-hf-4bit
4-bit
Text generation ↓ 107 · ♥ 1
Params
—
Weights
—
Mac memory
—

llama2 · updated 2024-01-03

phi-4-abliterated-4bit

from huihui-ai/phi-4-abliterated
4-bit
Text generation · huihui-ai ↓ 107 · ♥ 1
Params
15B
Weights
≈ 8.2 GB
Mac memory
16 GB+

mit · updated 2025-01-09

Qwen3.6-35B-A3B-AntiLoop-NVFP4

from N8Programs/Qwen3.6-35B-A3B-AntiLoop
Text generation · N8Programs ↓ 106 · ♥ 3
Params
7.1B
Weights
≈ 20.9 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-07-10

GLM-5-MXFP4-Q8

from zai-org/GLM-5
MXFP4
Text generation · zai-org ↓ 106 · ♥ 1
Params
744B
Weights
≈ 419 GB
Mac memory
512 GB+

mit · updated 2026-02-13

Llama-3.3-Swallow-70B-Instruct-v0.4-4bit

from tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4
4-bit
Text generation · tokyotech-llm ↓ 106 · ♥ 1
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+

llama3.3 · updated 2025-03-10

MagenticBrain-4bit

from microsoft/MagenticBrain
4-bit
Text generation · Microsoft · Phi ↓ 106 · ♥ 1
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

mit · updated 2026-07-29

ABEJA-Qwen2.5-32b-Japanese-v0.1-4bit

from abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1
4-bit
Text generation · abeja ↓ 106 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-01-27

ABEJA-Qwen2.5-32b-Japanese-v0.1-8bit

from abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1
8-bit
Text generation · abeja ↓ 106 · ♥ 0
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-01-27

Qwen3-1.7B-6bit

from Qwen/Qwen3-1.7B
6-bit
Text generation · Qwen ↓ 106 · ♥ 0
Params
1.7B
Weights
≈ 1.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

Laguna-S-2.1-oQ3e-fast

from poolside/Laguna-S-2.1
3-bit
Text generation · poolside ↓ 105 · ♥ 10
Params
118B
Weights
≈ 51.5 GB
Mac memory
64 GB+

openmdw-1.1 · updated 2026-07-24

Falcon3-1B-Instruct-4bit

from tiiuae/Falcon3-1B-Instruct
4-bit
Text generation · TII · Falcon ↓ 105 · ♥ 0
Params
1.7B
Weights
≈ 939 MB
Mac memory
8 GB+

falcon-llm-license · updated 2024-12-17

Qwen2.5-Coder-3B-bf16

from Qwen/Qwen2.5-Coder-3B
bf16
Text generation · Qwen ↓ 105 · ♥ 0
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

qwen-research · updated 2024-11-11

Yi-6B-Chat-4bit

from 01-ai/Yi-6B-Chat
4-bit
Text generation · 01.AI · Yi ↓ 105 · ♥ 0
Params
6.1B
Weights
≈ 3.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-05

gemma-4-31B-it-qat-assistant-8bit

from google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
8-bit
Text generation · Google · Gemma ↓ 105 · ♥ 0
Params
470M
Weights
≈ 499 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

plamo-2-1b

from pfnet/plamo-2-1b
Text generation · pfnet ↓ 104 · ♥ 4
Params
1.3B
Weights
≈ 5.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-15

GLM-4.6-5bit

from zai-org/GLM-4.6
5-bit
Text generation · zai-org ↓ 104 · ♥ 3
Params
353B
Weights
≈ 243 GB
Mac memory
512 GB+

mit · updated 2025-09-30

HY-MT1.5-1.8B-bf16

from tencent/HY-MT1.5-1.8B
bf16
Text generation · tencent ↓ 104 · ♥ 2
Params
1.8B
Weights
≈ 3.6 GB
Mac memory
8 GB+

updated 2026-01-03

Kimi-Linear-48B-A3B-Instruct-3bit

from moonshotai/Kimi-Linear-48B-A3B-Instruct
3-bit
Text generation · Moonshot · Kimi ↓ 104 · ♥ 2
Params
49B
Weights
≈ 21.5 GB
Mac memory
32 GB+

mit · updated 2026-01-22

SmolLM-1.7B-Instruct-4bit

mlx-community/SmolLM-1.7B-Instruct-4bit
4-bit
Text generation ↓ 104 · ♥ 2
Params
1.7B
Weights
≈ 963 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-07-16

Qwen3-0.6B-4bit-DWQ-053125

from Qwen/Qwen3-0.6B
4-bit DWQ
Text generation · Qwen ↓ 104 · ♥ 1
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-01

Wayfarer-Large-70B-Llama-3.3-4bit

from LatitudeGames/Wayfarer-Large-70B-Llama-3.3
4-bit
Text generation · LatitudeGames ↓ 104 · ♥ 1
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+

llama3.3 · updated 2025-02-20

Falcon-H1R-7B-4bit

from tiiuae/Falcon-H1R-7B
4-bit
Text generation · TII · Falcon ↓ 103 · ♥ 2
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

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

Llama-3-Swallow-8B-v0.1-8bit

mlx-community/Llama-3-Swallow-8B-v0.1-8bit
8-bit
Text generation ↓ 103 · ♥ 2
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3 · updated 2024-09-06

translategemma-27b-it-bf16

from google/translategemma-27b-it
bf16
Text generation · Google · Gemma ↓ 103 · ♥ 1
Params
27B
Weights
≈ 54.0 GB
Mac memory
64 GB+

gemma · updated 2026-02-07

LFM2.5-2.6B-5bit

from LiquidAI/LFM2.5-2.6B
5-bit
Text generation · LiquidAI ↓ 103 · ♥ 0
Params
2.7B
Weights
≈ 1.9 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

SmolLM2-360M-Instruct-6bit

from HuggingFaceTB/SmolLM2-360M-Instruct
6-bit
Text generation · Hugging Face ↓ 103 · ♥ 0
Params
362M
Weights
≈ 294 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-26

DeepSeek-V4-Flash-3bit-DQ

from deepseek-ai/DeepSeek-V4-Flash
3-bit
Text generation · DeepSeek ↓ 102 · ♥ 2
Params
284B
Weights
≈ 125 GB
Mac memory
192 GB+

mit · updated 2026-04-27

Inkling-NVFP4-mlx-4bit

from thinkingmachines/Inkling-NVFP4
4-bit
Text generation · thinkingmachines ↓ 102 · ♥ 2
Params
947B
Weights
≈ 581 GB
Mac memory
> 512 GB

apache-2.0 · updated 2026-07-17

Qwen2.5-72B-Instruct-6bit

from Qwen/Qwen2.5-72B-Instruct
6-bit
Text generation · Qwen ↓ 102 · ♥ 1
Params
73B
Weights
≈ 59.1 GB
Mac memory
96 GB+

qwen · updated 2024-11-24

Tiny-Pickle-v3-Coder-4bit

from vsan/tiny-pickle-v3-coder
4-bit
Text generation · vsan ↓ 102 · ♥ 1
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-08-06

deepseek-ai-DeepSeek-V4-Flash-3bit

from deepseek-ai/DeepSeek-V4-Flash
3-bit
Text generation · DeepSeek ↓ 102 · ♥ 1
Params
284B
Weights
≈ 125 GB
Mac memory
192 GB+

mit · updated 2026-04-24

OLMoE-1B-7B-0125-8bit

from allenai/OLMoE-1B-7B-0125
8-bit
Text generation · Ai2 · OLMo ↓ 102 · ♥ 0
Params
6.9B
Weights
≈ 7.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-16

Ling-2.6-flash-mlx-4bit-DWQ

from inclusionAI/Ling-2.6-flash
4-bit DWQ
Text generation · inclusionAI ↓ 101 · ♥ 7
Params
104B
Weights
≈ 58.6 GB
Mac memory
96 GB+

mit · updated 2026-04-30

MiniMax-M2.7-5bit

from MiniMaxAI/MiniMax-M2.7
5-bit
Text generation · MiniMaxAI ↓ 101 · ♥ 3
Params
229B
Weights
≈ 157 GB
Mac memory
192 GB+

modified-mit · updated 2026-04-12

Cydonia-24B-v3.1-4bit

from TheDrummer/Cydonia-24B-v3.1
4-bit
Text generation · TheDrummer ↓ 101 · ♥ 1
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+

updated 2025-06-25

LFM2.5-2.6B-mxfp4

from LiquidAI/LFM2.5-2.6B
MXFP4
Text generation · LiquidAI ↓ 101 · ♥ 1
Params
2.7B
Weights
≈ 1.5 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

Qwen2.5-0.5B-bf16

mlx-community/Qwen2.5-0.5B-bf16
bf16
Text generation ↓ 101 · ♥ 0
Params
494M
Weights
≈ 988 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

CodeLlama-7b-mlx

mlx-community/CodeLlama-7b-mlx
Text generation ↓ 100 · ♥ 10
Params
—
Weights
—
Mac memory
—

llama2 · updated 2023-12-20

Qwen3.5-REAP-97B-A10B-4bit

from OpenMOSE/Qwen3.5-REAP-97B-A10B
4-bit
Text generation · OpenMOSE ↓ 100 · ♥ 6
Params
97B
Weights
≈ 54.4 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-04-01

Qwen2.5-14B-Instruct-1M-bf16

from Qwen/Qwen2.5-14B-Instruct-1M
bf16
Text generation · Qwen ↓ 100 · ♥ 3
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-01-26

DeepSeek-V3.2-mlx-5bit

from deepseek-ai/DeepSeek-V3.2
5-bit
Text generation · DeepSeek ↓ 100 · ♥ 2
Params
672B
Weights
≈ 462 GB
Mac memory
> 512 GB

mit · updated 2026-01-06

MiniMax-M2.5-8bit

from MiniMaxAI/MiniMax-M2.5
8-bit
Text generation · MiniMaxAI ↓ 100 · ♥ 2
Params
229B
Weights
≈ 243 GB
Mac memory
512 GB+

modified-mit · updated 2026-02-13

gemma-3-4b-it-4bit-DWQ

from google/gemma-3-4b-it
4-bit DWQ
Text generation · Google · Gemma ↓ 100 · ♥ 2
Params
4.6B
Weights
≈ 2.6 GB
Mac memory
8 GB+

gemma · updated 2025-05-14

K2-Horizon-7B-bf16

from IFM/K2-Horizon-7B
bf16
Text generation · IFM ↓ 99 · ♥ 0
Params
9.0B
Weights
≈ 18.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-09-30

Meta-Llama-3.1-8B-Instruct-3bit

from meta-llama/Llama-3.1-8B-Instruct
3-bit
Text generation · Meta · Llama ↓ 99 · ♥ 0
Params
8.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+

llama3.1 · updated 2024-11-23

Qwen1.5-MoE-A2.7B-4bit

mlx-community/Qwen1.5-MoE-A2.7B-4bit
4-bit
Text generation ↓ 99 · ♥ 0
Params
14B
Weights
≈ 8.5 GB
Mac memory
16 GB+

tongyi-qianwen · updated 2024-04-02

gemma-3-1b-it-qat-8bit

from google/gemma-3-1b-it
8-bit
Text generation · Google · Gemma ↓ 99 · ♥ 0
Params
1.3B
Weights
≈ 1.4 GB
Mac memory
8 GB+

gemma · updated 2025-04-18

Mellum-4b-base-4bit

from JetBrains/Mellum-4b-base
4-bit
Text generation · JetBrains ↓ 98 · ♥ 3
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-28

Qwen3-14B-bf16

from Qwen/Qwen3-14B
bf16
Text generation · Qwen ↓ 98 · ♥ 1
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-04-28

Qwen2.5-Coder-0.5B-8bit

from Qwen/Qwen2.5-Coder-0.5B
8-bit
Text generation · Qwen ↓ 98 · ♥ 0
Params
494M
Weights
≈ 525 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-11

llm-jp-3-7.2b-instruct3

from llm-jp/llm-jp-3-7.2b-instruct3
Text generation · llm-jp ↓ 98 · ♥ 0
Params
7.3B
Weights
≈ 14.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-02-05

sqlcoder-70b-alpha-4bit-mlx

mlx-community/sqlcoder-70b-alpha-4bit-mlx
4-bit
Text generation ↓ 97 · ♥ 6
Params
—
Weights
—
Mac memory
—

cc-by-sa-4.0 · updated 2024-02-01

aya-expanse-32b-8bit

from CohereLabs/aya-expanse-32b
8-bit
Text generation · Cohere ↓ 97 · ♥ 2
Params
32B
Weights
≈ 34.3 GB
Mac memory
48 GB+

cc-by-nc-4.0 · updated 2024-10-25

Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-2-bit

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
2-bit
Text generation · Goekdeniz-Guelmez ↓ 97 · ♥ 1
Params
15B
Weights
≈ 4.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-09

Olmo-3.1-32B-Instruct-8bit

from allenai/Olmo-3.1-32B-Instruct
8-bit
Text generation · Ai2 · OLMo ↓ 97 · ♥ 0
Params
32B
Weights
≈ 34.2 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-12-23