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

5,842 builds · page 88 of 98

Nanbeige4-3B-Thinking-2511-gabliterated-8bit

from Goekdeniz-Guelmez/Nanbeige4-3B-Thinking-2511-gabliterated
8-bit
Text generation · Goekdeniz-Guelmez ↓ 18 · ♥ 0
Params
3.9B
Weights
≈ 4.2 GB
Mac memory
8 GB+

updated 2026-01-13

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

from allenai/Olmo-3-7B-Instruct-SFT
6-bit
Text generation · Ai2 · OLMo ↓ 18 · ♥ 0
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-20

P1-VL-30B-A3B-6bit

from PRIME-RL/P1-VL-30B-A3B
6-bit
Vision + text · PRIME-RL ↓ 18 · ♥ 0
Params
31B
Weights
≈ 25.9 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-05-19

Qwen3.5-0.8B-mixed_3_4

mlx-community/Qwen3.5-0.8B-mixed_3_4
4-bit
Uncategorised ↓ 18 · ♥ 0
Params
204M
Weights
≈ 294 MB
Mac memory
8 GB+

updated 2026-03-02

Qwen3.5-0.8B-mixed_4_8

mlx-community/Qwen3.5-0.8B-mixed_4_8
4-bit
Uncategorised ↓ 18 · ♥ 0
Params
256M
Weights
≈ 323 MB
Mac memory
8 GB+

updated 2026-03-02

Ring-flash-linear-2.0-6bit

from inclusionAI/Ring-flash-linear-2.0
6-bit
Text generation · inclusionAI ↓ 18 · ♥ 0
Params
104B
Weights
≈ 84.6 GB
Mac memory
128 GB+

mit · updated 2025-11-02

Rivermind-Lux-12B-v1-6bit

from TheDrummer/Rivermind-Lux-12B-v1
6-bit
Text generation · TheDrummer ↓ 18 · ♥ 0
Params
12B
Weights
≈ 10.0 GB
Mac memory
16 GB+

updated 2025-06-06

SU-01-8bit

from Simplified-Reasoning/SU-01
8-bit
Text generation · Simplified-Reasoning ↓ 18 · ♥ 0
Params
31B
Weights
≈ 32.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-05-17

Tessa-T1-14B-mlx-4bit

from Tesslate/Tessa-T1-14B
4-bit
Text generation · Tesslate ↓ 18 · ♥ 0
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-25

VibeVoice-Realtime-0.5B-5bit

from Qwen/Qwen2.5-0.5B
5-bit
Text to speech · Qwen ↓ 18 · ♥ 0
Params
1.0B
Weights
≈ 754 MB
Mac memory
8 GB+

mit · updated 2025-12-15

XortronCriminalComputingConfig-8bit

from darkc0de/XortronCriminalComputingConfig
8-bit
Text generation · darkc0de ↓ 18 · ♥ 0
Params
24B
Weights
≈ 25.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-02-19

XortronCriminalComputingConfig-bfloat16

from darkc0de/XortronCriminalComputingConfig
Text generation · darkc0de ↓ 18 · ♥ 0
Params
24B
Weights
≈ 47.1 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-02-18

Yi-1.5-6B-4bit

mlx-community/Yi-1.5-6B-4bit
4-bit
Uncategorised ↓ 18 · ♥ 0
Params
6.1B
Weights
≈ 3.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-05-13

campplus_chinese_16k_common

mlx-community/campplus_chinese_16k_common
Uncategorised ↓ 18 · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2026-01-15

deepcogito-cogito-v1-preview-qwen-14B-bf16

from deepcogito/cogito-v1-preview-qwen-14B
bf16
Text generation · deepcogito ↓ 18 · ♥ 0
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-04-08

dolphin-2.2-yi-34b-200k

mlx-community/dolphin-2.2-yi-34b-200k
Uncategorised ↓ 18 · ♥ 0
Params
34B
Weights
≈ 68.8 GB
Mac memory
96 GB+

yi-license · updated 2024-04-07

encodec-48khz-bfloat16

mlx-community/encodec-48khz-bfloat16
Uncategorised ↓ 18 · ♥ 0
Params
17M
Weights
≈ 34 MB
Mac memory
8 GB+

other · updated 2024-09-18

falcon-mamba-7b-8bit

from tiiuae/falcon-mamba-7b
8-bit
Uncategorised · TII · Falcon ↓ 18 · ♥ 0
Params
7.3B
Weights
≈ 7.7 GB
Mac memory
16 GB+

falcon-mamba-7b-license · updated 2024-11-15

federico-upl-model

mlx-community/federico-upl-model
Text generation ↓ 18 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-03-13

gemma-3-270m-it-qat-bf16

from google/gemma-3-270m-it-qat
bf16
Text generation · Google · Gemma ↓ 18 · ♥ 0
Params
436M
Weights
≈ 872 MB
Mac memory
8 GB+

gemma · updated 2025-08-09

gemma-3-270m-qat-8bit

from google/gemma-3-270m-qat
8-bit
Text generation · Google · Gemma ↓ 18 · ♥ 0
Params
436M
Weights
≈ 463 MB
Mac memory
8 GB+

gemma · updated 2025-08-09

lift-oQ3.5

from datalab-to/lift
3-bit
Vision + text · datalab-to ↓ 18 · ♥ 0
Params
9.4B
Weights
≈ 4.8 GB
Mac memory
8 GB+

openrail · updated 2026-06-27

mamba-370m-hf-f32

from state-spaces/mamba-370m-hf
Text generation · state-spaces ↓ 18 · ♥ 0
Params
372M
Weights
≈ 1.5 GB
Mac memory
8 GB+

updated 2024-09-21

mamba2-1.3b-4bit

mlx-community/mamba2-1.3b-4bit
4-bit
Uncategorised ↓ 18 · ♥ 0
Params
211M
Weights
≈ 181 MB
Mac memory
8 GB+

updated 2025-01-21

mamba2-370m

from rokyang/mamba2-370m-hf
Uncategorised · rokyang ↓ 18 · ♥ 0
Params
368M
Weights
≈ 737 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-21

mistral-22B-v0.2-8bit-mlx

mlx-community/mistral-22B-v0.2-8bit-mlx
8-bit
Uncategorised ↓ 18 · ♥ 0
Params
22B
Weights
≈ 23.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2024-04-13

mistral-ft-optimized-1227-4bit-mlx

mlx-community/mistral-ft-optimized-1227-4bit-mlx
4-bit
Uncategorised ↓ 18 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-01-14

paligemma2-10b-mix-224-4bit

mlx-community/paligemma2-10b-mix-224-4bit
4-bit
Vision + text ↓ 18 · ♥ 0
Params
9.7B
Weights
≈ 6.0 GB
Mac memory
16 GB+

gemma · updated 2025-02-19

paligemma2-3b-mix-224-3bit

mlx-community/paligemma2-3b-mix-224-3bit
3-bit
Vision + text ↓ 18 · ♥ 0
Params
3.0B
Weights
≈ 2.0 GB
Mac memory
8 GB+

gemma · updated 2025-02-19

paligemma2-3b-mix-224-6bit

mlx-community/paligemma2-3b-mix-224-6bit
6-bit
Vision + text ↓ 18 · ♥ 0
Params
3.0B
Weights
≈ 3.0 GB
Mac memory
8 GB+

gemma · updated 2025-02-19

paligemma2-3b-mix-448-6bit

mlx-community/paligemma2-3b-mix-448-6bit
6-bit
Vision + text ↓ 18 · ♥ 0
Params
3.0B
Weights
≈ 3.0 GB
Mac memory
8 GB+

gemma · updated 2025-02-19

qwq-bakeneko-32b-4bit

from rinna/qwq-bakeneko-32b
4-bit
Text generation · rinna ↓ 18 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-13

Llama-3-8B-16K-8bit

mlx-community/Llama-3-8B-16K-8bit
8-bit
Uncategorised ↓ 17 · ♥ 3
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

updated 2024-04-23

OpenELM-450M-Instruct

mlx-community/OpenELM-450M-Instruct
Uncategorised ↓ 17 · ♥ 3
Params
457M
Weights
≈ 914 MB
Mac memory
8 GB+

apple-sample-code-license · updated 2024-04-24

DR-Venus-4B-SFT-mlx-8Bit

from inclusionAI/DR-Venus-4B-SFT
8-bit
Uncategorised · inclusionAI ↓ 17 · ♥ 2
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2026-04-29

Phi-lthy4-mlx-8Bit

from SicariusSicariiStuff/Phi-lthy4
8-bit
Uncategorised · SicariusSicariiStuff ↓ 17 · ♥ 2
Params
12B
Weights
≈ 12.7 GB
Mac memory
24 GB+

mit · updated 2025-06-18

Qwen3-30B-A3B-Instruct-2507-8bit-DWQ

mlx-community/Qwen3-30B-A3B-Instruct-2507-8bit-DWQ
8-bit DWQ
Uncategorised ↓ 17 · ♥ 2
Params
31B
Weights
≈ 11.9 GB
Mac memory
16 GB+

updated 2025-07-30

reka-flash-3-mlx-4bit

mlx-community/reka-flash-3-mlx-4bit
4-bit
Uncategorised ↓ 17 · ♥ 2
Params
21B
Weights
≈ 11.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-12

LLaDA-8B-Instruct-mlx-fp16

from GSAI-ML/LLaDA-8B-Instruct
fp16
Text generation · GSAI-ML ↓ 17 · ♥ 1
Params
8.0B
Weights
≈ 16.0 GB
Mac memory
24 GB+

mit · updated 2025-03-12

Llama-OuteTTS-1.0-1B-3bit

mlx-community/Llama-OuteTTS-1.0-1B-3bit
3-bit
Text to speech ↓ 17 · ♥ 1
Params
1.2B
Weights
≈ 546 MB
Mac memory
8 GB+

cc-by-nc-sa-4.0 · updated 2025-05-19

NAFNet-REDS-width64

from megvii-research/NAFNet
Image to image · megvii-research ↓ 17 · ♥ 1
Params
68M
Weights
≈ 272 MB
Mac memory
8 GB+

mit · updated 2026-06-04

OpenSora-VAE-v1.2

mlx-community/OpenSora-VAE-v1.2
Uncategorised ↓ 17 · ♥ 1
Params
393M
Weights
≈ 787 MB
Mac memory
8 GB+

other · updated 2024-08-02

icup-pii-redact-general

mlx-community/icup-pii-redact-general
4-bit
Uncategorised ↓ 17 · ♥ 1
Params
193M
Weights
≈ 164 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-11-06

zephyr-7b-beta-4bit

mlx-community/zephyr-7b-beta-4bit
4-bit
Text generation ↓ 17 · ♥ 1
Params
—
Weights
—
Mac memory
—

mit · updated 2023-12-27

Hercules-5.0-Qwen2-1.5B-8bits

mlx-community/Hercules-5.0-Qwen2-1.5B-8bits
8-bit
Uncategorised ↓ 17 · ♥ 0
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-06-28

JOSIE-1.1-4B-Instruct-mxfp4

from Goekdeniz-Guelmez/JOSIE-1.1-4B-Instruct
MXFP4
Text generation · Goekdeniz-Guelmez ↓ 17 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

mit · updated 2026-03-09

JOSIE-1.1-4B-Thinking-4bit

from Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking
4-bit
Text generation · Goekdeniz-Guelmez ↓ 17 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

mit · updated 2026-03-09

JOSIE-1.1-4B-Thinking-mxfp4

from Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking
MXFP4
Text generation · Goekdeniz-Guelmez ↓ 17 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

mit · updated 2026-03-09

Jedi-7B-1080p-bf16

from Qwen/Qwen2.5-VL-7B-Instruct
bf16
Vision + text · Qwen ↓ 17 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-01

Josie-r1-4b-PoC-8bit

from Goekdeniz-Guelmez/Josie-r1-4b-PoC-bf16
8-bit
Text generation · Goekdeniz-Guelmez ↓ 17 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2025-12-18

Josie-r1-4b-bfloat16

from Goekdeniz-Guelmez/Josie-r1-4b
Text generation · Goekdeniz-Guelmez ↓ 17 · ♥ 0
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2025-12-18

Josiefied-Qwen3-0.6B-gabliterated-8bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-gabliterated-v1
8-bit
Text generation · Goekdeniz-Guelmez ↓ 17 · ♥ 0
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+

updated 2026-01-26

Kumru-2B-6bit

from vngrs-ai/Kumru-2B
6-bit
Text generation · vngrs-ai ↓ 17 · ♥ 0
Params
2.4B
Weights
≈ 1.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-15

LFM2-2.6B-Exp-5bit

from LiquidAI/LFM2-2.6B-Exp
5-bit
Text generation · LiquidAI ↓ 17 · ♥ 0
Params
2.6B
Weights
≈ 1.8 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-12-26

LFM2.5-1.2B-Base-8bit

from LiquidAI/LFM2.5-1.2B-Base
8-bit
Text generation · LiquidAI ↓ 17 · ♥ 0
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+

other · updated 2026-01-06

LFM2.5-1.2B-JP-6bit

from LiquidAI/LFM2.5-1.2B-JP
6-bit
Text generation · LiquidAI ↓ 17 · ♥ 0
Params
1.2B
Weights
≈ 951 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-06

Llama-2-7b-WikiChat-mlx

mlx-community/Llama-2-7b-WikiChat-mlx
Uncategorised ↓ 17 · ♥ 0
Params
—
Weights
—
Mac memory
—

llama2 · updated 2024-01-09