Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,842 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 47 of 49 · clear filters

Falcon-H1-Tiny-Multilingual-100M-Base-8bit

from tiiuae/Falcon-H1-Tiny-Multilingual-100M-Base
8-bit
Text generation · TII · Falcon ↓ 20 · ♥ 0
Params
108M
Weights
≈ 115 MB
Mac memory
8 GB+

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

Falcon-H1-Tiny-R-0.6B-pre-GRPO-8bit

from tiiuae/Falcon-H1-Tiny-R-0.6B-pre-GRPO
8-bit
Text generation · TII · Falcon ↓ 20 · ♥ 0
Params
622M
Weights
≈ 662 MB
Mac memory
8 GB+

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

Granite-4.0-350m-gabliterated-8bit

from Goekdeniz-Guelmez/Granite-4.0-350m-gabliterated
8-bit
Text generation · Goekdeniz-Guelmez ↓ 20 · ♥ 0
Params
352M
Weights
≈ 374 MB
Mac memory
8 GB+

updated 2026-01-23

Homunculus-4bit

from arcee-ai/Homunculus
4-bit
Text generation · arcee-ai ↓ 20 · ♥ 0
Params
12B
Weights
≈ 7.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-06-03

Homunculus-8bit

from arcee-ai/Homunculus
8-bit
Text generation · arcee-ai ↓ 20 · ♥ 0
Params
12B
Weights
≈ 13.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-03

Hunyuan-0.5B-Instruct-8bit

from tencent/Hunyuan-0.5B-Instruct
8-bit
Text generation · tencent ↓ 20 · ♥ 0
Params
539M
Weights
≈ 573 MB
Mac memory
8 GB+

updated 2025-08-04

Hunyuan-7B-Instruct-6bit

from tencent/Hunyuan-7B-Instruct
6-bit
Text generation · tencent ↓ 20 · ♥ 0
Params
7.5B
Weights
≈ 6.1 GB
Mac memory
16 GB+

tencent-license · updated 2025-02-08

JOSIE-4B-Instruct-6bit

from Goekdeniz-Guelmez/JOSIE-4B-Instruct
6-bit
Text generation · Goekdeniz-Guelmez ↓ 20 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

mit · updated 2026-02-12

JOSIE-IT1-Qwen3-0.6B-bfloat16

from Goekdeniz-Guelmez/JOSIE-IT1-Qwen3-0.6B
Text generation · Goekdeniz-Guelmez ↓ 20 · ♥ 0
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+

updated 2026-01-12

LFM2.5-1.2B-Base-6bit

from LiquidAI/LFM2.5-1.2B-Base
6-bit
Text generation · LiquidAI ↓ 20 · ♥ 0
Params
1.2B
Weights
≈ 951 MB
Mac memory
8 GB+

other · updated 2026-01-06

LFM2.5-1.2B-JP-5bit

from LiquidAI/LFM2.5-1.2B-JP
5-bit
Text generation · LiquidAI ↓ 20 · ♥ 0
Params
1.2B
Weights
≈ 805 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-06

Llama-3-Karamaru-v1-4bit

from SakanaAI/Llama-3-Karamaru-v1
4-bit
Text generation · SakanaAI ↓ 20 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3 · updated 2025-04-01

Marx-3B-V2-6bit

from acrastt/Marx-3B-V2
6-bit
Text generation · acrastt ↓ 20 · ♥ 0
Params
3.4B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-18

Olmo-3-1125-32B-4bit

from allenai/Olmo-3-1125-32B
4-bit
Text generation · Ai2 · OLMo ↓ 20 · ♥ 0
Params
32B
Weights
≈ 18.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-11-21

Olmo-3-7B-Think-6bit

from allenai/Olmo-3-7B-Think
6-bit
Text generation · Ai2 · OLMo ↓ 20 · ♥ 0
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-21

Pleias-RAG-1B-4-bit

from PleIAs/Pleias-RAG-1B
4-bit
Text generation · PleIAs ↓ 20 · ♥ 0
Params
1.2B
Weights
≈ 673 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-24

Pleias-RAG-350M-bf16

from PleIAs/Pleias-RAG-350M
bf16
Text generation · PleIAs ↓ 20 · ♥ 0
Params
353M
Weights
≈ 707 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-24

Polaris-4B-Preview-bf16

from POLARIS-Project/Polaris-4B-Preview
bf16
Text generation · POLARIS-Project ↓ 20 · ♥ 0
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-07-03

Ring-flash-linear-2.0-128k-8bit

from inclusionAI/Ring-flash-linear-2.0-128k
8-bit
Text generation · inclusionAI ↓ 20 · ♥ 0
Params
104B
Weights
≈ 111 GB
Mac memory
128 GB+

mit · updated 2025-11-03

Rivermind-Lux-12B-v1-8bit

from TheDrummer/Rivermind-Lux-12B-v1
8-bit
Text generation · TheDrummer ↓ 20 · ♥ 0
Params
12B
Weights
≈ 13.0 GB
Mac memory
24 GB+

updated 2025-06-06

Tessa-T1-14B-mlx-4bit

from Tesslate/Tessa-T1-14B
4-bit
Text generation · Tesslate ↓ 20 · ♥ 0
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-25

deepcogito-cogito-v1-preview-llama-70B-bf16

from deepcogito/cogito-v1-preview-llama-70B
bf16
Text generation · deepcogito ↓ 20 · ♥ 0
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+

llama3.1 · updated 2025-04-09

deepcogito-cogito-v1-preview-llama-8B-8bit

from deepcogito/cogito-v1-preview-llama-8B
8-bit
Text generation · deepcogito ↓ 20 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.1 · updated 2025-04-08

gemma-3-270m-it-qat-6bit

from google/gemma-3-270m-it-qat
6-bit
Text generation · Google · Gemma ↓ 20 · ♥ 0
Params
436M
Weights
≈ 354 MB
Mac memory
8 GB+

gemma · updated 2025-08-09

granite-4.0-350m-base-5bit

from ibm-granite/granite-4.0-350m-base
5-bit
Text generation · IBM · Granite ↓ 20 · ♥ 0
Params
352M
Weights
≈ 242 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

granite-4.0-350m-base-6bit

from ibm-granite/granite-4.0-350m-base
6-bit
Text generation · IBM · Granite ↓ 20 · ♥ 0
Params
352M
Weights
≈ 286 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

granite-4.0-h-350m-base-8bit

from ibm-granite/granite-4.0-h-350m-base
8-bit
Text generation · IBM · Granite ↓ 20 · ♥ 0
Params
340M
Weights
≈ 362 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

orpheus-3b-0.1-pretrained-bf16

from canopylabs/orpheus-3b-0.1-pretrained
bf16
Text generation · canopylabs ↓ 20 · ♥ 0
Params
3.3B
Weights
≈ 6.6 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-04-02

s1.1-32B-4bit

from simplescaling/s1.1-32B
4-bit
Text generation · simplescaling ↓ 20 · ♥ 0
Params
1.8B
Weights
≈ 1000 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-14

shisa-v2-qwen2.5-32b-4bit

from shisa-ai/shisa-v2-qwen2.5-32b
4-bit
Text generation · shisa-ai ↓ 20 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-04-15

XBai-o4-8bit

from MetaStoneTec/XBai-o4
8-bit
Text generation · MetaStoneTec ↓ 19 · ♥ 4
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-08-02

mamba-370m-hf-f16

from state-spaces/mamba-370m-hf
Text generation · state-spaces ↓ 19 · ♥ 1
Params
372M
Weights
≈ 743 MB
Mac memory
8 GB+

updated 2024-09-21

EXAONE-Deep-2.4B-6bit

from LGAI-EXAONE/EXAONE-Deep-2.4B
6-bit
Text generation · LGAI-EXAONE ↓ 19 · ♥ 0
Params
2.4B
Weights
≈ 2.0 GB
Mac memory
8 GB+

exaone · updated 2025-03-18

EXAONE-Deep-32B-6bit

from LGAI-EXAONE/EXAONE-Deep-32B
6-bit
Text generation · LGAI-EXAONE ↓ 19 · ♥ 0
Params
32B
Weights
≈ 26.0 GB
Mac memory
32 GB+

exaone · updated 2025-03-18

Falcon-E-1B-Instruct-6bit

from tiiuae/Falcon-E-1B-Instruct
6-bit
Text generation · TII · Falcon ↓ 19 · ♥ 0
Params
426M
Weights
≈ 351 MB
Mac memory
8 GB+

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

Falcon3-1B-Instruct-8bit

from tiiuae/Falcon3-1B-Instruct
8-bit
Text generation · TII · Falcon ↓ 19 · ♥ 0
Params
1.7B
Weights
≈ 1.8 GB
Mac memory
8 GB+

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

FastContext-1.0-4B-SFT-4bit

from ShaunGves/FastContext-1.0-4B-SFT
4-bit
Text generation · ShaunGves ↓ 19 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

mit · updated 2026-07-08

Fathom-R1-14B-6bit

from FractalAIResearch/Fathom-R1-14B
6-bit
Text generation · FractalAIResearch ↓ 19 · ♥ 0
Params
15B
Weights
≈ 12.0 GB
Mac memory
16 GB+

mit · updated 2025-06-06

Fathom-R1-14B-8bit

from FractalAIResearch/Fathom-R1-14B
8-bit
Text generation · FractalAIResearch ↓ 19 · ♥ 0
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+

mit · updated 2025-06-06

Hunyuan-A13B-Instruct-bf16

from tencent/Hunyuan-A13B-Instruct
bf16
Text generation · tencent ↓ 19 · ♥ 0
Params
80B
Weights
≈ 161 GB
Mac memory
192 GB+

tencent-hunyuan-a13b · updated 2025-07-13

JOSIE-1.1-4B-Instruct-8bit

from Goekdeniz-Guelmez/JOSIE-1.1-4B-Instruct
8-bit
Text generation · Goekdeniz-Guelmez ↓ 19 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

mit · updated 2026-03-09

Jan-v1-4B-6bit

from janhq/Jan-v1-4B
6-bit
Text generation · janhq ↓ 19 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-12

Josiefied-Olmo-3-7B-Instruct-abliterated-v1-6bit

from Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1
6-bit
Text generation · Goekdeniz-Guelmez ↓ 19 · ♥ 0
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+

updated 2025-11-25

LLaDA2.0-flash-6bit

from inclusionAI/LLaDA2.0-flash
6-bit
Text generation · inclusionAI ↓ 19 · ♥ 0
Params
103B
Weights
≈ 83.6 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-11-26

LongCat-Flash-Thinking-2601-8bit

from meituan-longcat/LongCat-Flash-Thinking-2601
8-bit
Text generation · meituan-longcat ↓ 19 · ♥ 0
Params
561B
Weights
≈ 596 GB
Mac memory
> 512 GB

mit · updated 2026-01-18

Olmo-3-7B-Instruct-SFT-8bit

from allenai/Olmo-3-7B-Instruct-SFT
8-bit
Text generation · Ai2 · OLMo ↓ 19 · ♥ 0
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-20

Olmo-3-7B-Think-SFT-6bit

from allenai/Olmo-3-7B-Think-SFT
6-bit
Text generation · Ai2 · OLMo ↓ 19 · ♥ 0
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-21

Olmo-3-7B-Think-SFT-8bit

from allenai/Olmo-3-7B-Think-SFT
8-bit
Text generation · Ai2 · OLMo ↓ 19 · ♥ 0
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-21

Ring-flash-linear-2.0-128k-6bit

from inclusionAI/Ring-flash-linear-2.0-128k
6-bit
Text generation · inclusionAI ↓ 19 · ♥ 0
Params
104B
Weights
≈ 84.6 GB
Mac memory
128 GB+

mit · updated 2025-11-07

SERA-8B-GA-6bit

from allenai/SERA-8B-GA
6-bit
Text generation · Ai2 · OLMo ↓ 19 · ♥ 0
Params
8.2B
Weights
≈ 6.7 GB
Mac memory
16 GB+

updated 2026-01-27

SU-01-mxfp4

from Simplified-Reasoning/SU-01
MXFP4
Text generation · Simplified-Reasoning ↓ 19 · ♥ 0
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-05-16

UNA-TheBeagle-7b-v1-4bit-mlx

mlx-community/UNA-TheBeagle-7b-v1-4bit-mlx
4-bit
Text generation ↓ 19 · ♥ 0
Params
—
Weights
—
Mac memory
—

cc-by-nc-nd-4.0 · updated 2024-01-14

federico-upl-model

mlx-community/federico-upl-model
Text generation ↓ 19 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-03-13

gemma-3-270m-qat-bf16

from google/gemma-3-270m-qat
bf16
Text generation · Google · Gemma ↓ 19 · ♥ 0
Params
436M
Weights
≈ 872 MB
Mac memory
8 GB+

gemma · updated 2025-08-09

granite-4.0-h-350m-6bit

from ibm-granite/granite-4.0-h-350m
6-bit
Text generation · IBM · Granite ↓ 19 · ♥ 0
Params
340M
Weights
≈ 277 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

mamba-790m-hf-f32

from state-spaces/mamba-790m-hf
Text generation · state-spaces ↓ 19 · ♥ 0
Params
793M
Weights
≈ 3.2 GB
Mac memory
8 GB+

updated 2024-09-21

JOSIE-4B-Instruct-8bit

from Goekdeniz-Guelmez/JOSIE-4B-Instruct
8-bit
Text generation · Goekdeniz-Guelmez ↓ 18 · ♥ 1
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

mit · updated 2026-02-12

EXAONE-Deep-2.4B-3bit

from LGAI-EXAONE/EXAONE-Deep-2.4B
3-bit
Text generation · LGAI-EXAONE ↓ 18 · ♥ 0
Params
2.4B
Weights
≈ 1.1 GB
Mac memory
8 GB+

exaone · updated 2025-03-18

Gabliterated-Qwen3-0.6B-6bit

from Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated-Dev
6-bit
Text generation · Goekdeniz-Guelmez ↓ 18 · ♥ 0
Params
596M
Weights
≈ 484 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-28

Hunyuan-7B-Instruct-3bit

from tencent/Hunyuan-7B-Instruct
3-bit
Text generation · tencent ↓ 18 · ♥ 0
Params
7.5B
Weights
≈ 3.3 GB
Mac memory
8 GB+

tencent-license · updated 2025-02-08